© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46186
    Prev
    Next
    INDEX
    Explanations

    overs: old, impl, ight, ized

    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
    你
    0.86
    ור
    0.86
    ل
    0.80
    ب
    0.80
    ad
    0.79
    い
    0.79
    ين
    0.77
    ↵
    0.76
    ak
    0.76
    ev
    0.76
    POSITIVE LOGITS
    0.82
     d
    0.69
    (
    0.68
     SAFETY
    0.68
     modèle
    0.66
     QUESTION
    0.66
     które
    0.65
    ’
    0.65
     BEEN
    0.64
     à
    0.64
    Activations Density 0.000%

    No Known Activations