© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112903
    Prev
    Next
    INDEX
    Explanations

    Scotch, code, episkopos

    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_2_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
    le
    1.49
    n
    1.36
    ।
    1.33
    ל
    1.27
    ר
    1.24
    d
    1.23
    ن
    1.22
    :
    1.13
    ي
    1.13
    ir
    1.13
    POSITIVE LOGITS
    िक
    0.87
     escuchar
    0.77
     atteint
    0.76
    ってしまう
    0.73
     সময়ে
    0.72
     tiver
    0.72
     형태
    0.72
     averiguar
    0.72
     quitar
    0.71
     जिसके
    0.71
    Activations Density 0.000%

    No Known Activations