© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109413
    Prev
    Next
    INDEX
    Explanations

    mysqldump

    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_2_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
    ot
    1.16
    AST
    1.11
    ע
    1.09
    ARE
    1.07
    '
    1.06
    ACH
    1.02
    k
    1.01
    lma
    0.99
    <0x87>
    0.98
    ਕ
    0.98
    POSITIVE LOGITS
    \
    1.36
    that
    1.33
    ре
    1.29
     subsid
    1.13
     disparu
    1.13
    ことを
    1.09
     negocio
    1.09
     що
    1.08
     duelo
    1.08
    ш
    1.08
    Activations Density 0.000%

    No Known Activations