© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139927
    Prev
    Next
    INDEX
    Explanations

    ooh, oof, oh

    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_12_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
    ի
    0.63
    (""))
    0.57
    к
    0.54
    ut
    0.50
    ^)
    0.49
    were
    0.49
     radiographs
    0.48
    ri
    0.48
    क
    0.47
     கொடுக்க
    0.46
    POSITIVE LOGITS
    t
    0.54
     niveaux
    0.52
     który
    0.50
     britannique
    0.50
     Ét
    0.50
     necessários
    0.49
     trở
    0.48
     produt
    0.48
     ethic
    0.48
     revisited
    0.47
    Activations Density 0.000%

    No Known Activations