© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4825
    Prev
    Next
    INDEX
    Explanations

    angle brackets and other miscellaneous markup tokens.

    oai_token-act-pair · gemini-2.0-flash

    ▁»

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     snippetHide
    -1.00
    Tikang
    -0.97
    ⓧ
    -0.92
    RenderAtEndOf
    -0.90
    LookAnd
    -0.88
    MessageOf
    -0.88
    tvguidetime
    -0.87
    
    -0.85
     مشين
    -0.84
    Transkript
    -0.83
    POSITIVE LOGITS
     
    0.69
     and
    0.60
     as
    0.58
     in
    0.57
    ,
    0.56
     at
    0.55
     by
    0.53
     on
    0.53
     over
    0.52
     that
    0.52
    Activations Density 2.498%

    No Known Activations