© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90593
    Prev
    Next
    INDEX
    Explanations

    minimize

    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_11_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
     använda
    0.69
     utilizz
    0.65
     använder
    0.63
    <unused446>
    0.62
     använd
    0.61
     법칙
    0.60
     использу
    0.59
     incisions
    0.59
     alterations
    0.58
     utilizzare
    0.57
    POSITIVE LOGITS
    t
    0.77
    W
    0.60
    0.59
    the
    0.56
    of
    0.55
    Name
    0.53
    D
    0.52
    V
    0.52
    on
    0.51
    s
    0.51
    Activations Density 0.006%

    No Known Activations