© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130679
    Prev
    Next
    INDEX
    Explanations

    fanatical, often

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_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
    W
    1.63
    B
    1.54
    are
    1.29
    and
    1.27
    D
    1.23
    H
    1.23
    M
    1.22
    F
    1.22
    at
    1.20
    1
    1.19
    POSITIVE LOGITS
    ют
    0.99
    ления
    0.85
    ление
    0.85
     dargestellt
    0.84
    تى
    0.82
    يك
    0.82
    ט
    0.82
    );">
    0.79
    0.79
     crecer
    0.78
    Activations Density 0.000%

    No Known Activations