© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213841
    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_5_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
    t
    1.85
    ↵
    1.64
    ↵↵
    1.38
     a
    1.13
    ."
    1.04
    be
    1.02
    5
    1.02
    g
    0.98
    wa
    0.97
    на
    0.96
    POSITIVE LOGITS
    N
    1.38
    ो
    1.33
    전
    1.30
    و
    1.24
    ו
    1.23
    ى
    1.22
    Л
    1.22
    V
    1.16
    ור
    1.14
    の違い
    1.12
    Activations Density 0.000%

    No Known Activations