© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203665
    Prev
    Next
    INDEX
    Explanations

    fur, ink, trapping

    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_12_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
    ｡
    0.59
     cani
    0.58
     Kanye
    0.57
     tuxedo
    0.57
     furs
    0.56
     vatth
    0.56
     lingerie
    0.54
     വിവാ
    0.54
     limousine
    0.54
    $,
    0.53
    POSITIVE LOGITS
    érations
    0.52
    க்கும்
    0.50
    ية
    0.48
    кован
    0.48
     otro
    0.46
    ých
    0.45
    ਰਾ
    0.45
    㮆
    0.45
    quier
    0.44
    bücher
    0.44
    Activations Density 0.000%

    No Known Activations