© 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. 1961
    Prev
    Next
    INDEX
    Explanations

    long negative numbers with many decimal places

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms

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

    say numbers

    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
    rungsseite
    -0.85
     ujednoznacz
    -0.70
     ModelExpression
    -0.65
     كومونز
    -0.63
    ImageContext
    -0.60
     تضيفلها
    -0.58
     disambiguazione
    -0.56
    MethodManager
    -0.55
    CppMethod
    -0.54
     Pasture
    -0.54
    POSITIVE LOGITS
     intptr
    0.60
    estar
    0.52
    ftagPool
    0.49
    ClientSize
    0.49
    Token
    0.49
    estars
    0.47
     Parr
    0.47
    Tokens
    0.46
    getResultList
    0.46
     sett
    0.45
    Activations Density 3.026%

    No Known Activations