© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12073
    Prev
    Next
    INDEX
    Explanations

    instances of asking, telling, or saying, often related to requests or statements.

    oai_token-act-pair · gemini-2.0-flash

    asked

    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
     uſe
    -0.56
    assertAll
    -0.55
     EconPapers
    -0.55
     NDEBUG
    -0.52
    LLocation
    -0.52
     depositphotos
    -0.52
    riction
    -0.52
     Reverso
    -0.52
     Gospels
    -0.51
     męska
    -0.51
    POSITIVE LOGITS
     whether
    0.91
     what
    0.71
    .*")]
    0.70
    whether
    0.70
     who
    0.68
     if
    0.67
     about
    0.66
     mergeFrom
    0.66
     مشين
    0.63
    yntaxException
    0.63
    Activations Density 8.900%

    No Known Activations