© 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. 58135
    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
    -
    0.96
    م
    0.95
    وم
    0.84
    3
    0.82
    يل
    0.80
    ات
    0.78
    de
    0.78
    i
    0.78
    ৫
    0.77
    6
    0.75
    POSITIVE LOGITS
     علی
    0.75
     فی
    0.68
     imbued
    0.67
     tyrannical
    0.67
     antérieure
    0.66
     обита
    0.66
     delectable
    0.65
    ಂಕ್
    0.64
     aspirated
    0.64
     tục
    0.64
    Activations Density 0.000%

    No Known Activations