© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9702
    Prev
    Next
    INDEX
    Explanations

    mentions of physical interface elements, such as keyboards or game controllers

    oai_token-act-pair · gemini-2.0-flash

    keyboard

    np_max-act-logits · 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
     autorytatywna
    -0.73
    ImageContext
    -0.67
     nahilalakip
    -0.65
    hyrchwyd
    -0.64
    canActivate
    -0.63
    bootstrapcdn
    -0.63
    tagHelperRunner
    -0.61
    rrggbb
    -0.60
    ьаж
    -0.59
     Paglinawan
    -0.59
    POSITIVE LOGITS
    omeness
    0.58
    DoubleQuotes
    0.53
     Gland
    0.50
    NOPQRST
    0.46
     Yank
    0.44
    ರು
    0.44
     Gron
    0.43
     scroll
    0.43
    __((
    0.43
    pron
    0.43
    Activations Density 4.398%

    No Known Activations