© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10913
    Prev
    Next
    INDEX
    Explanations

    code blocks containing `else` and encompassing curly braces or parentheses

    oai_token-act-pair · gemini-2.0-flash

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     ſy
    -0.71
     bershka
    -0.70
     betweenstory
    -0.70
     doubtnut
    -0.68
     ―――――
    -0.66
    GraphicsUnit
    -0.66
     ẞ
    -0.66
    RectangleBorder
    -0.66
    <bos>
    -0.65
    enumii
    -0.65
    POSITIVE LOGITS
    庁
    0.51
    paramref
    0.47
     C
    0.47
    ⇑
    0.47
     bru
    0.46
     prior
    0.44
    はじめに
    0.44
     async
    0.43
     este
    0.43
     res
    0.43
    Activations Density 0.640%

    No Known Activations