© 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. 4190
    Prev
    Next
    INDEX
    Explanations

    the word "tan", sometimes also activating on words near it

    oai_token-act-pair · gemini-2.0-flash

    tan

    np_max-act · gemini-2.0-flash
    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
    NameInMap
    -0.62
    ({
    -0.57
    sproz
    -0.55
    ){\
    -0.53
    ([\
    -0.52
    },{
    -0.50
    ={\
    -0.49
    .");
    -0.49
    etcode
    -0.49
    .
    -0.49
    POSITIVE LOGITS
    istoitu
    0.68
     Tasman
    0.68
    ptonshire
    0.65
    fony
    0.63
     transfieras
    0.63
     plagio
    0.61
     extingu
    0.60
     Tinto
    0.60
    AndEndTag
    0.60
    trums
    0.59
    Activations Density 1.287%

    No Known Activations