© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15132
    Prev
    Next
    INDEX
    Explanations

    names and words associated with speaking, especially in the context of formal statements or news.

    oai_token-act-pair · gemini-2.0-flash

    said, added

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ########.
    -0.88
    IntoConstraints
    -0.73
    Ver
    -0.63
    StructEnd
    -0.60
     Ver
    -0.60
     ModelExpression
    -0.59
    UnusedPrivate
    -0.57
     nakalista
    -0.55
     lenker
    -0.54
    DIPSETTING
    -0.54
    POSITIVE LOGITS
    XmlAccessType
    0.59
    XmlEnum
    0.54
    jsxFileName
    0.49
    σθαι
    0.49
    볍
    0.48
    matchCondition
    0.48
    ayak
    0.44
    RTSC
    0.43
     ᾿
    0.43
    slideUp
    0.43
    Activations Density 0.873%

    No Known Activations