© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133888
    Prev
    Next
    INDEX
    Explanations

    scavenger hunt

    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_6_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
    ك
    1.07
    ᵐ
    0.95
     individuo
    0.94
    tól
    0.94
     варианты
    0.93
    favor
    0.88
    ToDO
    0.88
    lots
    0.87
     современные
    0.87
     únicamente
    0.86
    POSITIVE LOGITS
    on
    1.13
     is
    1.13
    ab
    1.11
    "
    1.05
     or
    0.93
    am
    0.92
    um
    0.86
     not
    0.86
     one
    0.85
    ast
    0.84
    Activations Density 0.000%

    No Known Activations