© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246058
    Prev
    Next
    INDEX
    Explanations

    events held

    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_40_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
    ucle
    0.44
    कून
    0.42
    target
    0.41
     Lahore
    0.39
    assets
    0.38
    bul
    0.38
    錯
    0.38
    軟
    0.38
    ଠ
    0.38
     carre
    0.38
    POSITIVE LOGITS
    HALL
    0.39
    시켜
    0.39
     Over
    0.38
    を選択
    0.37
    总部
    0.37
     Halls
    0.37
    Hall
    0.36
    弔
    0.36
     headquarters
    0.36
     halls
    0.36
    Activations Density 0.000%

    No Known Activations