© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10434
    Prev
    Next
    INDEX
    Explanations

    equation and figure references

    oai_token-act-pair · gemini-2.0-flash

    code and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ?)
    -1.97
    ?).
    -1.95
    )</
    -1.92
    ’)
    -1.91
    !)
    -1.91
    ),”
    -1.90
     ?)
    -1.89
    ’).
    -1.86
    ).</
    -1.84
    …)
    -1.84
    POSITIVE LOGITS
    </h4>
    1.07
     (
    1.03
    </blockquote>
    0.70
    （
    0.62
    ↵↵↵↵
    0.49
    (
    0.49
    ↵↵↵↵↵
    0.48
    .
    0.46
    <h4>
    0.44
     （
    0.42
    Activations Density 3.497%

    No Known Activations