© 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. 228332
    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
     that
    1.20
    az
    1.04
    ü
    1.01
     was
    1.00
    é
    0.98
    ist
    0.96
    ak
    0.96
    .
    0.95
     as
    0.93
    um
    0.90
    POSITIVE LOGITS
    म
    1.55
    ל
    1.17
    ल
    1.16
    to
    1.13
    یا
    1.05
    मधील
    1.04
    ד
    0.97
    ри
    0.94
    К
    0.94
    nome
    0.93
    Activations Density 0.000%

    No Known Activations