© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3385
    Prev
    Next
    INDEX
    Explanations

    clauses separated by em dashes.

    oai_token-act-pair · gemini-2.0-flash

    em dash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     L
    -0.57
     &
    -0.54
     The
    -0.52
     /
    -0.49
     *
    -0.46
    ↵↵
    -0.44
     Te
    -0.44
    "
    -0.43
    .
    -0.43
    get
    -0.43
    POSITIVE LOGITS
     pinulongan
    0.89
    parsedMessage
    0.81
     becauſe
    0.80
     whoſe
    0.77
    })));
    0.76
     ModelExpression
    0.75
     /\.(
    0.75
    }))
    0.75
    expandindo
    0.74
    })*/
    0.74
    Activations Density 0.536%

    No Known Activations