© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42732
    Prev
    Next
    INDEX
    Explanations

    Ingebrigtsen Bergman

    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
     of
    0.82
     at
    0.77
     (
    0.77
    im
    0.76
    ↵
    0.74
    ו
    0.73
     ins
    0.65
     indispensable
    0.64
     are
    0.63
     explanatory
    0.62
    POSITIVE LOGITS
    る
    0.68
    انت
    0.65
    Ẳ
    0.65
    toInt
    0.64
    EXIT
    0.63
    下記の
    0.62
    נות
    0.61
    Aslamualaikum
    0.61
    toJson
    0.60
    ضاف
    0.59
    Activations Density 0.000%

    No Known Activations