© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58651
    Prev
    Next
    INDEX
    Explanations

    diving behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     carina
    0.12
     conformément
    0.12
     straighten
    0.11
     brighten
    0.11
    К
    0.11
     بالإضافة
    0.11
     endregion
    0.11
    包括
    0.11
     MARKET
    0.11
    EndZ
    0.11
    POSITIVE LOGITS
    ς
    0.12
    rias
    0.12
    when
    0.12
    s
    0.12
    í
    0.11
    <0x93>
    0.11
    )
    0.11
     когда
    0.11
    сти
    0.11
    ).
    0.11
    Activations Density 0.002%

    No Known Activations