© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194094
    Prev
    Next
    INDEX
    Explanations

    been considered

    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_9_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
     RtlOverlay
    0.46
     ойной
    0.44
    макраты
    0.44
    ˄
    0.44
    ูล
    0.43
     мүмк
    0.43
    ).—
    0.43
     ক্ষম
    0.43
    พิเศษ
    0.43
    忒
    0.43
    POSITIVE LOGITS
     urine
    0.60
     stylish
    0.59
    ing
    0.57
     what
    0.57
     her
    0.57
     hair
    0.56
    ler
    0.55
    string
    0.54
    inė
    0.54
    less
    0.52
    Activations Density 0.000%

    No Known Activations