© 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. 12900
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest things are difficult or hard to find

    oai_token-act-pair · gemini-2.0-flash

    uncommon or technical terms related to tagging or metadata

    np_token-act-pair-logits · gpt-4o-mini
    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
     R
    -0.54
    R
    -0.52
     Sig
    -0.49
    thera
    -0.49
    M
    -0.49
    vacy
    -0.48
     besides
    -0.47
     Référence
    -0.47
     baffle
    -0.46
    ولة
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.90
     CreateTagHelper
    0.85
     surla
    0.81
     ainfi
    0.80
     tartalomajánló
    0.80
     ſeveral
    0.80
     Eſ
    0.77
    ſelves
    0.77
     purpoſe
    0.76
     avoient
    0.75
    Activations Density 7.071%

    No Known Activations