© 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. 85596
    Prev
    Next
    INDEX
    Explanations

    junk food, junkyard, mail

    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
    ری
    0.81
    یع
    0.81
    น
    0.80
    ン
    0.77
    ব
    0.73
    ラ
    0.73
    지
    0.68
    사
    0.67
    嚆
    0.67
    מיני
    0.67
    POSITIVE LOGITS
    на
    0.59
    ne
    0.57
    ".
    0.57
     sanit
    0.57
    ã
    0.57
    ulte
    0.56
    ",
    0.54
    kont
    0.54
     legitim
    0.53
     company
    0.52
    Activations Density 0.000%

    No Known Activations