© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3911
    Prev
    Next
    INDEX
    Explanations

    mixed uppercase and lowercase text, often acronyms or abbreviations, sometimes near numbers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     photolibrary
    -1.18
     Cæsar
    -1.16
     negroes
    -1.09
     Moslem
    -1.03
     demurrer
    -1.02
     Shakspeare
    -1.02
     Mahomet
    -1.00
     poffible
    -1.00
     endregion
    -0.99
     eletrônico
    -0.99
    POSITIVE LOGITS
    <bos>
    1.35
     P
    0.72
     B
    0.72
     an
    0.67
     W
    0.66
     a
    0.63
    B
    0.63
     “
    0.62
     and
    0.60
     C
    0.60
    Activations Density 1.596%

    No Known Activations