© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4076
    Prev
    Next
    INDEX
    Explanations

    Java or C code, specifically import statements and the slf4j logging library

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    assertArray
    -0.67
    </tfoot>
    -0.64
    __':
    -0.63
    migrationBuilder
    -0.63
    assertEquals
    -0.62
    Soorten
    -0.58
    __':
    -0.57
    kloped
    -0.57
     />);
    -0.57
    )\}$
    -0.56
    POSITIVE LOGITS
    GIVEREF
    0.76
    <bos>
    0.68
     kiệm
    0.54
    ETER
    0.53
    '
    0.51
     financières
    0.49
     
    0.49
     darb
    0.49
    あれば
    0.48
    icksburg
    0.48
    Activations Density 0.144%

    No Known Activations