© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193835
    Prev
    Next
    INDEX
    Explanations

    list items followed by punctuation or specific words

    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_9_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
    '
    0.57
    a
    0.53
    া
    0.52
    д
    0.52
     Were
    0.47
    ın
    0.46
     Outline
    0.46
    '$,
    0.46
    т
    0.45
     Assn
    0.43
    POSITIVE LOGITS
     AcOEt
    0.52
    rese
    0.48
    𝗥
    0.48
     αρ
    0.47
     პროფილი
    0.47
    UD
    0.46
    validated
    0.46
    ent
    0.45
     الدین
    0.45
     הע
    0.45
    Activations Density 0.000%

    No Known Activations