© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12570
    Prev
    Next
    INDEX
    Explanations

    many different short sequences of characters of various lengths, possibly from multiple languages

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    BeginContext
    -0.60
    forChild
    -0.48
    enteric
    -0.47
    autorest
    -0.47
    ArgsConstructor
    -0.44
    Géographie
    -0.44
    AspNetCore
    -0.43
    boz
    -0.41
    AndEndTag
    -0.41
     lern
    -0.41
    POSITIVE LOGITS
     Wikispecies
    0.69
    sizeCache
    0.65
    évaluateur
    0.63
    LookAnd
    0.62
     "..\..\..\
    0.61
    QMetaType
    0.59
     "..\..\
    0.58
    getRuntime
    0.57
    Filmografie
    0.57
     OFDb
    0.56
    Activations Density 0.560%

    No Known Activations