© 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. 34922
    Prev
    Next
    INDEX
    Explanations

    PM, AM, times

    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
    の
    0.67
    Unter
    0.64
    の発
    0.62
    な
    0.60
    २
    0.60
    の位置
    0.58
    ");
    0.58
    );
    0.57
    Izq
    0.57
    udarstven
    0.57
    POSITIVE LOGITS
    ان
    0.69
    고
    0.64
    ам
    0.63
    PM
    0.62
     worldRank
    0.60
    times
    0.58
    alle
    0.57
    ate
    0.57
    arding
    0.56
    atka
    0.56
    Activations Density 0.249%

    No Known Activations