© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12407
    Prev
    Next
    INDEX
    Explanations

    mentions of someone speaking, telling, or otherwise communicating information.

    oai_token-act-pair · gemini-2.0-flash

    telling

    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
     Majefty
    -0.71
     pleaſure
    -0.70
     Theſe
    -0.69
     Jefus
    -0.68
    SourceChecksum
    -0.65
     Diſ
    -0.65
     Reſ
    -0.60
     '\\;'
    -0.60
     ModelExpression
    -0.59
     myſelf
    -0.59
    POSITIVE LOGITS
     Se
    0.56
    ração
    0.52
     us
    0.52
    !*\
    0.51
    जन
    0.50
    AutoScaleMode
    0.49
    ها
    0.48
    neté
    0.48
    EDITOR
    0.48
    QMetaType
    0.47
    Activations Density 0.344%

    No Known Activations