© 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-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130646
    Prev
    Next
    INDEX
    Explanations

    squeaky voice or toys

    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_1_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
    1.20
    ת
    1.15
     to
    1.06
     chinese
    0.98
     ano
    0.96
     canadian
    0.95
     bộ
    0.95
     beak
    0.94
     with
    0.92
     la
    0.91
    POSITIVE LOGITS
    a
    1.85
    an
    1.71
    i
    1.63
    0
    1.63
    া
    1.63
    ي
    1.51
    ه
    1.44
    ে
    1.36
    <0x0D>
    1.28
    ;
    1.25
    Activations Density 0.000%

    No Known Activations