© 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. 39520
    Prev
    Next
    INDEX
    Explanations

    pretrainingtraining objectiveshared key

    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
    ه
    0.86
    ש
    0.86
    in
    0.84
    ول
    0.80
    تع
    0.79
    تح
    0.79
    ir
    0.77
    t
    0.77
    f
    0.75
    ض
    0.75
    POSITIVE LOGITS
    0.92
    I
    0.90
     व
    0.68
    ı
    0.64
     l
    0.59
     ו
    0.58
     dale
    0.58
     THAN
    0.56
    IFF
    0.55
     critic
    0.55
    Activations Density 0.006%

    No Known Activations