© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11335
    Prev
    Next
    INDEX
    Explanations

    words used when talking about sources and how questions or requests relate to the speaker

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     am
    -2.95
     Am
    -2.63
    Am
    -2.53
     AM
    -2.44
    AM
    -2.13
    am
    -2.03
     Ам
    -1.55
     Amm
    -1.54
     Ami
    -1.50
     ame
    -1.45
    POSITIVE LOGITS
    addCriterion
    0.56
    ựng
    0.47
    ContextHolder
    0.44
    findOrFail
    0.43
    extrême
    0.42
    ietf
    0.42
    uevos
    0.42
     constitucional
    0.42
     newBuilder
    0.41
    ioutil
    0.41
    Activations Density 1.991%

    No Known Activations