© 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. 14033
    Prev
    Next
    INDEX
    Explanations

    words that are likely to indicate an opinion or review is being expressed

    oai_token-act-pair · gemini-2.0-flash

    artistic evaluations

    np_max-act-logits · 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
     تانيه
    -0.71
    AddHtmlAttribute
    -0.58
     disambiguazione
    -0.57
    Gambas
    -0.57
    InstrumentedTest
    -0.54
    новништво
    -0.54
    RenderAtEndOf
    -0.52
    ebvre
    -0.51
    UnknownFieldSet
    -0.51
     Paglinawan
    -0.50
    POSITIVE LOGITS
    LookAnd
    0.56
     élas
    0.50
    SourceChecksum
    0.50
     Lit
    0.49
     ég
    0.48
    OCCURRED
    0.48
     litté
    0.48
    ubar
    0.46
     bParam
    0.46
    WebControls
    0.46
    Activations Density 10.297%

    No Known Activations