© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27711
    Prev
    Next
    INDEX
    Explanations

    babe, Siren, Sister, Betty

    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_10_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
    ה
    0.80
    ו
    0.60
    ه
    0.57
    a
    0.57
    Đ
    0.54
    Το
    0.53
    u
    0.52
    트
    0.52
    Š
    0.51
    Γ
    0.51
    POSITIVE LOGITS
     الار
    0.46
     Би
    0.44
     ለአ
    0.44
     బీ
    0.44
     الذين
    0.43
     생
    0.43
     Ва
    0.42
     cowl
    0.42
     프랑
    0.42
     দুই
    0.42
    Activations Density 0.018%

    No Known Activations