© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89994
    Prev
    Next
    INDEX
    Explanations

    cancel out or eliminate

    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_23_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
    ෙහි
    0.37
    ;.
    0.36
     चंद्रशेखर
    0.36
    ել
    0.35
    ші
    0.35
     cellophane
    0.34
     hôm
    0.34
     হল
    0.34
    গতকাল
    0.34
    ൃ
    0.34
    POSITIVE LOGITS
    va
    0.39
    feat
    0.36
     feat
    0.36
     maquillaje
    0.36
    amb
    0.35
     Kerja
    0.35
    nač
    0.35
     Makeup
    0.35
    ifai
    0.35
    awks
    0.34
    Activations Density 0.068%

    No Known Activations