© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87431
    Prev
    Next
    INDEX
    Explanations

    hazardous materials

    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
    ة
    0.95
    ن
    0.83
    il
    0.81
    Y
    0.78
    ين
    0.73
    C
    0.72
     It
    0.72
    ir
    0.69
    ün
    0.69
    它
    0.69
    POSITIVE LOGITS
    などの
    0.76
     فی
    0.76
    transfected
    0.73
    の研究
    0.70
    ᱕
    0.69
    ینی
    0.68
     لی
    0.68
    以下の
    0.68
    手の
    0.68
     यही
    0.67
    Activations Density 0.000%

    No Known Activations