© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13024
    Prev
    Next
    INDEX
    Explanations

    words and phrases used as the foundation or reason for a decision.

    oai_token-act-pair · gemini-2.0-flash

    basis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    })));
    -0.83
    }))
    -0.77
    HandlerContext
    -0.73
    ThroughAttribute
    -0.61
    InputBorder
    -0.61
     urso
    -0.60
    complexContent
    -0.59
    RenderAtEndOf
    -0.59
    tanleria
    -0.57
    ValueStyle
    -0.57
    POSITIVE LOGITS
     of
    0.51
    ಷ್
    0.48
    intera
    0.44
     single
    0.44
     free
    0.44
    unków
    0.44
     segi
    0.44
    škai
    0.44
    esterno
    0.43
     full
    0.43
    Activations Density 1.803%

    No Known Activations