© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194327
    Prev
    Next
    INDEX
    Explanations

    breakdown after certain 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_15_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
     luscious
    0.59
     했다
    0.54
    o
    0.53
     historical
    0.52
     allure
    0.50
    devkit
    0.50
     progenitors
    0.50
    "),
    0.49
     muse
    0.49
     nostalgic
    0.49
    POSITIVE LOGITS
    Methyl
    0.45
    unati
    0.44
    Medical
    0.44
     Médico
    0.44
    фта
    0.44
    鲔
    0.44
     Origami
    0.43
    瓈
    0.43
    Tagged
    0.43
    MsgCallBack
    0.43
    Activations Density 0.000%

    No Known Activations