© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12719
    Prev
    Next
    INDEX
    Explanations

    people contacting other people in a position of authority

    oai_token-act-pair · gemini-2.0-flash

    from/by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Wikimedijinoj
    -0.55
    endpush
    -0.52
    PerformLayout
    -0.50
     CreateTagHelper
    -0.49
    HtmlAttribute
    -0.49
     <",
    -0.49
    icitis
    -0.48
     reç
    -0.45
    ->__
    -0.45
    principalColumn
    -0.45
    POSITIVE LOGITS
    DispatchToProps
    0.59
    })`
    0.57
     <<<<<<<<<<<<<<
    0.57
    RegisterType
    0.55
    osus
    0.53
    िन्न
    0.53
    ссора
    0.52
    WarningLevel
    0.52
    område
    0.51
    uyên
    0.51
    Activations Density 5.158%

    No Known Activations