© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68804
    Prev
    Next
    INDEX
    Explanations

    face up or down

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    iquée
    0.40
    🫦
    0.40
    cone
    0.38
     rattled
    0.35
    off
    0.35
    មើល
    0.35
     squir
    0.35
    bell
    0.34
     pruned
    0.34
    left
    0.34
    POSITIVE LOGITS
     face
    0.49
     Knudsen
    0.43
     ಭ
    0.40
    ັກ
    0.40
    BusinessType
    0.39
    getCQL
    0.39
    LOY
    0.38
    cini
    0.38
     breathe
    0.38
     चेहरा
    0.38
    Activations Density 0.002%

    No Known Activations