© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24934
    Prev
    Next
    INDEX
    Explanations

    what followed by pronoun or verb

    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_10_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
    fin
    0.53
     Arbeiten
    0.50
    fen
    0.49
    _
    0.49
    fif
    0.49
    fers
    0.48
    রা
    0.48
     გამოყენ
    0.47
    Await
    0.46
    is
    0.46
    POSITIVE LOGITS
    s
    0.58
     volition
    0.57
    ا
    0.55
    ק
    0.54
    도
    0.53
     theses
    0.53
    드
    0.53
    ے
    0.52
    า
    0.50
     к
    0.49
    Activations Density 0.069%

    No Known Activations