© 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. 122718
    Prev
    Next
    INDEX
    Explanations

    what happens when

    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
    ty
    0.85
    to
    0.84
    ५
    0.82
    ten
    0.81
    nu
    0.77
    ni
    0.75
    ta
    0.73
    ny
    0.73
    ke
    0.73
    tr
    0.72
    POSITIVE LOGITS
    ي
    0.84
     élément
    0.77
    ి
    0.77
     čty
    0.75
     aquest
    0.75
     legate
    0.73
     arbres
    0.72
    מ
    0.71
     avaient
    0.71
     шесть
    0.70
    Activations Density 0.000%

    No Known Activations