© 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. 112214
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    0
    0.97
    9
    0.81
    and
    0.67
    7
    0.66
    8
    0.61
    ın
    0.59
    ore
    0.59
    <0x80>
    0.59
    5
    0.57
    Fall
    0.56
    POSITIVE LOGITS
    ن
    0.98
    ل
    0.91
     of
    0.86
    س
    0.85
    з
    0.77
    ス
    0.75
    ל
    0.75
     at
    0.73
    л
    0.73
    ਰ
    0.72
    Activations Density 0.000%

    No Known Activations