© 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. 90279
    Prev
    Next
    INDEX
    Explanations

    motte, Mot, mots, 持

    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
     ఉంట
    0.77
     كه
    0.72
     dividido
    0.71
    ia
    0.70
     سي
    0.70
     will
    0.69
    };
    0.68
    سى
    0.67
     చూ
    0.66
    ция
    0.66
    POSITIVE LOGITS
    ۔
    1.19
    2
    1.07
    ।
    1.05
    n
    1.02
    nj
    0.95
    nent
    0.93
    ت
    0.93
    nelle
    0.91
    ن
    0.89
    nar
    0.89
    Activations Density 0.000%

    No Known Activations