© 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. 130257
    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
    in
    1.33
    n
    1.10
    this
    1.01
    il
    1.00
    er
    0.98
     other
    0.98
    te
    0.98
     this
    0.96
     he
    0.95
    id
    0.95
    POSITIVE LOGITS
    '
    1.73
    It
    1.03
    ’
    1.03
    ায়
    1.01
    اء
    0.96
    osomes
    0.93
     eleições
    0.93
    "
    0.93
    increases
    0.92
    ாவில்
    0.91
    Activations Density 0.000%

    No Known Activations