© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 102804
    Prev
    Next
    INDEX
    Explanations

    scars

    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_44_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
     pink
    0.43
    pink
    0.40
    Pink
    0.40
     lingk
    0.38
    ໄດ້
    0.37
     current
    0.37
     amarelo
    0.37
    황
    0.37
    Financial
    0.36
    핑크
    0.36
    POSITIVE LOGITS
    atay
    0.39
    ၚ
    0.38
     Bien
    0.37
     TEN
    0.37
     بخوان
    0.37
     softness
    0.36
     Biss
    0.36
     Qh
    0.36
     softer
    0.36
    ahua
    0.36
    Activations Density 0.001%

    No Known Activations