© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4056
    Prev
    Next
    INDEX
    Explanations

    a mix of errors, code snippets, and advice

    oai_token-act-pair · gemini-2.0-flash

    Computer code/data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ']],
    -1.12
    __*/
    -1.11
    '])){
    -1.04
    __':
    -1.02
    '});
    -0.98
    ']?>
    -0.95
    .")]
    -0.95
    >*/
    -0.95
    ))){
    -0.94
    ']]
    -0.94
    POSITIVE LOGITS
    +#+#
    0.53
    PreferredItem
    0.52
    ↵↵
    0.47
    </strong>
    0.47
    ↵
    0.46
    0.44
    jerc
    0.42
    ENDIAN
    0.41
    RatingBar
    0.40
    λης
    0.40
    Activations Density 1.789%
    No Known Activations