© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10457
    Prev
    Next
    INDEX
    Explanations

    sports related words or phrases

    oai_token-act-pair · gemini-2.0-flash

    foreign language tokens or programming terminology

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

    in

    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
    orteur
    -0.55
    hangi
    -0.50
     astore
    -0.50
    plc
    -0.48
    verns
    -0.48
    CGRectMake
    -0.45
    dess
    -0.45
    Fordítás
    -0.44
    dles
    -0.43
    itects
    -0.43
    POSITIVE LOGITS
     دیکھیے
    0.67
    Viitteet
    0.65
    Autoritní
    0.65
    IndentedString
    0.59
    featureID
    0.57
    reportWebVitals
    0.56
    Спољашње
    0.56
    ISupport
    0.56
     femei
    0.56
    InitVars
    0.55
    Activations Density 0.919%

    No Known Activations