© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126825
    Prev
    Next
    INDEX
    Explanations

    betaxolol Bertram olol Tower Heng

    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_3_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
    3
    0.77
    \
    0.74
    OP
    0.72
    2
    0.70
    Berkeley
    0.70
    -
    0.69
    ある
    0.66
     serem
    0.62
    os
    0.60
     Berkeley
    0.60
    POSITIVE LOGITS
    л
    0.82
    pt
    0.66
    pá
    0.66
    p
    0.64
    pio
    0.63
    க்கும்
    0.62
    ма
    0.61
    ках
    0.61
    य
    0.60
    rbind
    0.59
    Activations Density 0.000%

    No Known Activations