© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90495
    Prev
    Next
    INDEX
    Explanations

    hazards and dread

    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_3_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
    ك
    1.02
    د
    0.94
    t
    0.82
    ка
    0.79
    ت
    0.78
    д
    0.71
    ب
    0.70
    т
    0.67
    скольку
    0.64
    ع
    0.63
    POSITIVE LOGITS
    า
    0.71
    ור
    0.65
    ]
    0.63
    (
    0.61
    ومي
    0.55
    ното
    0.55
    な
    0.53
    有
    0.52
     sicherlich
    0.52
     सिखा
    0.52
    Activations Density 0.038%

    No Known Activations