© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214450
    Prev
    Next
    INDEX
    Explanations

    Cthulhu Mythos

    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_5_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
     οπο
    0.94
     UART
    0.93
     た
    0.93
     powied
    0.90
    این
    0.88
     밝혔
    0.88
    িক
    0.87
     ی
    0.86
     지
    0.85
     bergantung
    0.85
    POSITIVE LOGITS
    ле
    1.40
    то
    1.38
    性
    1.30
    ט
    1.29
    ك
    1.28
    ص
    1.25
    ב
    1.24
    p
    1.21
    ка
    1.20
    те
    1.20
    Activations Density 0.000%

    No Known Activations