© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197696
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
    ა
    0.94
    ة
    0.93
    as
    0.93
    ри
    0.92
    i
    0.92
    ла
    0.91
    are
    0.88
    -
    0.86
    ار
    0.84
    ح
    0.82
    POSITIVE LOGITS
    秇
    0.66
     in
    0.63
     komt
    0.59
    那么
    0.58
    1
    0.58
     पिछड़ा
    0.57
    agem
    0.57
     ومع
    0.55
     бил
    0.54
    ᱛ
    0.54
    Activations Density 0.000%

    No Known Activations