© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6735
    Prev
    Next
    INDEX
    Explanations

    list()

    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_39_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
     CFT
    0.40
    stris
    0.40
    錡
    0.40
    인다
    0.40
    PSE
    0.39
    스코
    0.39
    CFT
    0.39
     Иң
    0.39
    ဉ
    0.39
    დეს
    0.38
    POSITIVE LOGITS
     bank
    0.43
     elabor
    0.40
    Map
    0.37
    ೋಷ
    0.37
     accurate
    0.36
     dialog
    0.36
    ems
    0.35
    흡
    0.35
    Cliff
    0.35
     Cliff
    0.35
    Activations Density 0.013%

    No Known Activations