© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4248
    Prev
    Next
    INDEX
    Explanations

    text discussing launching products and Amazon Web Services, particularly authentication and access

    oai_token-act-pair · gemini-2.0-flash

    terms related to data processing and management

    np_token-act-pair-logits · gpt-4o-mini

    immediate access, real-time processing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -1.00
     تضيفلها
    -0.99
    AutoScaleMode
    -0.84
     дописавши
    -0.77
    StoryboardSegue
    -0.75
     فريبيس
    -0.71
     Roskov
    -0.71
     bezeichneter
    -0.70
    IndentedString
    -0.70
     الحره
    -0.68
    POSITIVE LOGITS
     streaming
    0.54
     mobile
    0.52
     live
    0.51
     complete
    0.47
     accurate
    0.47
     predeceased
    0.46
     better
    0.46
     p
    0.46
     centralized
    0.45
     ter
    0.45
    Activations Density 2.521%

    No Known Activations