© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228143
    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_6_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
    ،
    0.97
    ir
    0.96
    á
    0.90
    ä
    0.89
     an
    0.88
    i
    0.86
    ed
    0.86
    _
    0.86
     can
    0.85
     I
    0.84
    POSITIVE LOGITS
    म
    1.34
    트
    1.15
    স
    1.13
    મ
    1.09
    л
    1.06
    ಮ
    1.06
    ন
    1.04
    いわ
    1.02
    ב
    1.01
    ਲ
    0.98
    Activations Density 0.000%

    No Known Activations