© 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. 157967
    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
    to
    1.31
    ق
    1.20
    ts
    1.15
     to
    1.13
     سید
    1.13
    nance
    1.11
    0
    1.09
    da
    1.04
    ds
    1.03
    dan
    1.02
    POSITIVE LOGITS
     for
    1.06
    它
    0.93
    ين
    0.91
    iz
    0.90
    ene
    0.90
    '
    0.89
     gouvernement
    0.88
    on
    0.86
    il
    0.85
     heißt
    0.82
    Activations Density 0.000%

    No Known Activations