© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46081
    Prev
    Next
    INDEX
    Explanations

    follow up questions

    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_10_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
    s
    0.99
     have
    0.91
     in
    0.86
     can
    0.82
     out
    0.77
     are
    0.76
    ä
    0.71
    ,
    0.70
     don
    0.70
     gibt
    0.68
    POSITIVE LOGITS
     Με
    0.91
     Через
    0.84
    filtering
    0.76
    frying
    0.70
    forest
    0.70
     뮤
    0.68
     Ре
    0.68
    ponses
    0.68
     Полу
    0.68
    那我們
    0.67
    Activations Density 0.001%

    No Known Activations