© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131540
    Prev
    Next
    INDEX
    Explanations

    scariest bedtime, Thai, thing, video, plot

    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_1_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
    EL
    1.30
     聞い
    1.29
    O
    1.16
     that
    1.16
    ای
    1.16
     whom
    1.12
    ED
    1.10
     have
    1.09
     書い
    1.09
    AL
    1.09
    POSITIVE LOGITS
    d
    1.88
    t
    1.69
    al
    1.56
    ى
    1.38
    ت
    1.30
    м
    1.25
    ра
    1.22
    et
    1.20
    v
    1.19
    re
    1.16
    Activations Density 0.000%

    No Known Activations