© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61174
    Prev
    Next
    INDEX
    Explanations

    rip, bench press

    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_11_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
     autom
    0.61
    BRI
    0.58
    ‘
    0.53
     replace
    0.53
     automate
    0.52
     overshoot
    0.52
     graze
    0.52
    וס
    0.52
     antid
    0.52
     daje
    0.52
    POSITIVE LOGITS
    isch
    0.57
    ike
    0.52
    lines
    0.52
     ܘ
    0.51
    ylethyl
    0.51
    igste
    0.51
    ilí
    0.51
    iny
    0.50
    kanal
    0.50
    eck
    0.50
    Activations Density 0.000%

    No Known Activations