© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9982
    Prev
    Next
    INDEX
    Explanations

    comments and annotations in code

    oai_token-act-pair · gemini-2.0-flash

    Code snippets/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    IntoConstraints
    -1.09
    DockStyle
    -0.86
     myſelf
    -0.84
     purpoſe
    -0.81
    principalTable
    -0.81
     Италијани
    -0.79
     pleaſure
    -0.78
     greateſt
    -0.77
     pinulongan
    -0.77
     itſelf
    -0.77
    POSITIVE LOGITS
     Sto
    0.48
    ffman
    0.48
    akah
    0.47
    urlpatterns
    0.45
    quant
    0.44
     realised
    0.43
     sto
    0.43
     char
    0.42
     للمعارف
    0.42
    Примечания
    0.42
    Activations Density 9.004%

    No Known Activations