© 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. 41104
    Prev
    Next
    INDEX
    Explanations

    db name identifiers

    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
    у
    0.74
     productColor
    0.72
     voj
    0.70
    UM
    0.63
    ид
    0.62
    見積
    0.61
     brighten
    0.61
    达成
    0.61
    рт
    0.60
    wm
    0.60
    POSITIVE LOGITS
    ه
    0.73
    a
    0.68
    ك
    0.68
    ו
    0.68
    ,"
    0.64
    ifying
    0.62
    ן
    0.60
    ה
    0.59
    ſs
    0.58
    情况下
    0.57
    Activations Density 0.010%

    No Known Activations