© 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. 46270
    Prev
    Next
    INDEX
    Explanations

    hallmark, sensor, effect

    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
    ل
    1.01
    J
    0.94
    ל
    0.91
    I
    0.83
    O
    0.77
    et
    0.75
     by
    0.75
    τή
    0.74
    ת
    0.72
    んですね
    0.72
    POSITIVE LOGITS
     is
    0.69
     fevereiro
    0.66
    t
    0.65
    dür
    0.64
     চিন্তা
    0.64
     carattere
    0.63
     are
    0.62
     הד
    0.62
     Гар
    0.62
     aspetti
    0.62
    Activations Density 0.000%

    No Known Activations