© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14802
    Prev
    Next
    INDEX
    Explanations

    articles followed by two-digit numbers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Tikang
    -0.93
     '\\;'
    -0.75
    RectangleBorder
    -0.74
     AppComponent
    -0.73
    Diweddarwch
    -0.72
    ChildScrollView
    -0.71
     MessageBoxIcon
    -0.69
    GraphicsUnit
    -0.68
    IsMutable
    -0.67
    ública
    -0.67
    POSITIVE LOGITS
     ©️
    0.46
    惯
    0.46
    :✨
    0.40
    owel
    0.40
     respecter
    0.39
    ウター
    0.39
     Einsch
    0.39
    ress
    0.39
    empuan
    0.38
    abestanden
    0.38
    Activations Density 0.712%

    No Known Activations