© 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. 214890
    Prev
    Next
    INDEX
    Explanations

    effectiveness of

    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
    ש
    0.98
    cknowled
    0.95
     bystand
    0.92
     demikian
    0.91
    ,
    0.90
    pose
    0.87
     علاقے
    0.86
     detergent
    0.86
     contagion
    0.86
     berkualitas
    0.85
    POSITIVE LOGITS
    ম
    1.58
    ల
    1.37
    }];
    1.35
    quela
    1.23
    ب
    1.22
    }]{
    1.19
    }
    1.19
     it
    1.16
    म
    1.16
    ى
    1.14
    Activations Density 0.001%

    No Known Activations