© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34903
    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_7_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
    0.67
    ش
    0.67
    ک
    0.62
    ל
    0.60
    ط
    0.59
    ح
    0.58
    나
    0.57
     advancements
    0.56
     outcomes
    0.55
    ह
    0.54
    POSITIVE LOGITS
     ד
    0.55
    oin
    0.54
     ח
    0.53
    ϝ
    0.53
    邙
    0.53
    hkse
    0.52
     הפ
    0.52
     Bourd
    0.52
    ulin
    0.51
     barra
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.