© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15998
    Prev
    Next
    INDEX
    Explanations

    words related to acceptance and approval, often in the context of relationships or societal issues.

    oai_token-act-pair · gemini-2.0-flash

    accept

    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
    enumii
    -1.15
     ModelExpression
    -1.14
    enumi
    -0.99
     himo
    -0.98
     Мексичка
    -0.96
    новниш
    -0.90
    __":
    -0.85
     InputDecoration
    -0.85
     otomatig
    -0.83
     AspNetCore
    -0.83
    POSITIVE LOGITS
     the
    0.55
     and
    0.53
     or
    0.46
     it
    0.46
     a
    0.44
     "
    0.42
    on
    0.41
     transfers
    0.41
     to
    0.41
    ,
    0.40
    Activations Density 7.076%

    No Known Activations