© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3154
    Prev
    Next
    INDEX
    Explanations

    words related to teeth

    oai_token-act-pair · gemini-2.0-flash

    technical terms in a specific context

    np_token-act-pair-logits · gpt-4o-mini

    dental and oral health

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    RectangleBorder
    -0.67
    DeleteBehavior
    -0.63
    mybatisplus
    -0.56
    TintMode
    -0.54
     الأصل
    -0.52
     Wikimedijinoj
    -0.51
    enderror
    -0.48
    HasAnnotation
    -0.48
    astify
    -0.46
    linalg
    -0.46
    POSITIVE LOGITS
    windowFixed
    0.65
    SequentialGroup
    0.63
    IsPostBack
    0.56
     Epit
    0.55
    ORAGE
    0.50
     ROOF
    0.49
     roof
    0.49
     toit
    0.48
    település
    0.48
    AutoSize
    0.48
    Activations Density 0.771%

    No Known Activations