© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11161
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers or math/scientific notation, often in context of code or citations

    oai_token-act-pair · gemini-2.0-flash

    Number 4

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ագրություններ
    -0.48
     must
    -0.48
     Must
    -0.45
    7
    -0.44
     seven
    -0.43
     seventh
    -0.42
    чин
    -0.42
     Seven
    -0.41
     Reiz
    -0.41
    iją
    -0.40
    POSITIVE LOGITS
    4
    0.88
     Fourth
    0.86
    cuatro
    0.83
    ⁴
    0.82
    RenderAtEndOf
    0.82
     keempat
    0.81
     quadruple
    0.81
     quartet
    0.79
    ④
    0.79
     four
    0.79
    Activations Density 9.301%

    No Known Activations