© 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. 108178
    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
    is
    1.49
    ת
    1.46
    in
    1.36
    it
    1.36
    us
    1.36
    ing
    1.30
    其他
    1.29
    ت
    1.28
    ין
    1.27
    ro
    1.23
    POSITIVE LOGITS
    ется
    1.31
    \
    1.26
    да
    1.09
    ne
    1.05
    ية
    1.03
    ре
    1.02
    द
    1.02
    مر
    1.00
    ление
    0.96
    áme
    0.96
    Activations Density 0.000%

    No Known Activations