© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13942
    Prev
    Next
    INDEX
    Explanations

    error handling and debugging messages

    oai_token-act-pair · gemini-2.0-flash

    variations of "bad"

    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
    </thead>
    -0.64
    ModelSerializer
    -0.58
    </tfoot>
    -0.56
    ATILE
    -0.48
    tur
    -0.46
    onyx
    -0.46
     Boyce
    -0.45
     Chwiliwch
    -0.45
    блица
    -0.44
    laise
    -0.43
    POSITIVE LOGITS
     bad
    0.78
    Bad
    0.77
     AssemblyProduct
    0.77
    bad
    0.74
     Bad
    0.72
     kasarigan
    0.69
     BAD
    0.63
    +#+#
    0.61
     StatelessWidget
    0.60
     beginnetje
    0.60
    Activations Density 10.283%

    No Known Activations