© 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. 4259
    Prev
    Next
    INDEX
    Explanations

    code snippets with lots of indentation

    oai_token-act-pair · gemini-2.0-flash

    words from multiple languages or technical terms

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

    6

    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
     critical
    -1.15
     Critical
    -1.07
    critical
    -1.06
    Critical
    -1.01
     CRITICAL
    -0.88
     crit
    -0.84
    CRITICAL
    -0.82
     kritis
    -0.80
    crit
    -0.79
    Crit
    -0.77
    POSITIVE LOGITS
     épo
    0.58
    Історія
    0.57
     resourceCulture
    0.56
     FetchType
    0.54
    ImageContext
    0.52
     متعلقه
    0.51
    StoryboardSegue
    0.50
     vors
    0.49
    Initializable
    0.49
     StatefulWidget
    0.48
    Activations Density 0.380%

    No Known Activations