© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38536
    Prev
    Next
    INDEX
    Explanations

    programming prefixes

    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_57_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
    ycle
    0.40
    iyy
    0.40
    idential
    0.38
     হান
    0.36
    ӗ
    0.36
    utely
    0.36
    rå
    0.35
     ば
    0.34
    пка
    0.34
    ياته
    0.34
    POSITIVE LOGITS
    olem
    0.41
    uja
    0.40
    ql
    0.38
    mere
    0.36
    ujen
    0.35
    peripheral
    0.35
     Kirchhoff
    0.35
    vres
    0.35
    สภาพ
    0.35
    tea
    0.35
    Activations Density 0.003%

    No Known Activations