© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43512
    Prev
    Next
    INDEX
    Explanations

    log or code followed by punctuation

    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_3_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
    in
    0.67
    지
    0.66
     London
    0.61
     や
    0.61
     bed
    0.59
     an
    0.56
    ून
    0.55
     Moscow
    0.55
    ಚ್ಚ
    0.55
    ಲ್ಲು
    0.55
    POSITIVE LOGITS
    (
    0.82
    ;
    0.82
    '
    0.73
    '};
    0.70
    _
    0.66
    ة
    0.65
    :
    0.64
    ing
    0.63
    <0x80>
    0.60
     SAMP
    0.60
    Activations Density 0.039%

    No Known Activations