© 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. 127532
    Prev
    Next
    INDEX
    Explanations

    safe and effective

    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
    یم
    0.73
     safely
    0.65
    s
    0.63
     تقسیم
    0.59
    ENTS
    0.57
     เนื่อง
    0.57
     تیم
    0.57
     بازی
    0.56
     เพราะ
    0.56
     SAFETY
    0.56
    POSITIVE LOGITS
    ة
    0.78
    та
    0.75
    ৫
    0.73
    تين
    0.71
    G
    0.71
    اب
    0.70
    ת
    0.70
    };
    0.67
    ле
    0.67
    ో
    0.66
    Activations Density 0.001%

    No Known Activations