© 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. 14735
    Prev
    Next
    INDEX
    Explanations

    mentions of mathematical formulas, tables, figures from technical papers.

    oai_token-act-pair · gemini-2.0-flash

    technical terminologies and functions in programming

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

    technical articles

    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
     limbs
    -0.47
    tawa
    -0.46
     braço
    -0.44
     subterrá
    -0.44
    Oriented
    -0.43
    combs
    -0.43
    ทรง
    -0.42
    Delimited
    -0.41
    sproble
    -0.41
     vst
    -0.41
    POSITIVE LOGITS
     ModelExpression
    0.89
    EndContext
    0.83
     nahilalakip
    0.79
    CreateModel
    0.71
    StoryboardSegue
    0.69
    encodeWith
    0.67
     disambiguazione
    0.67
    tagHelperRunner
    0.66
     AspNetCore
    0.64
    PageRoute
    0.63
    Activations Density 4.360%

    No Known Activations