© 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. 136771
    Prev
    Next
    INDEX
    Explanations

    February dates

    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
    ovjek
    0.19
     ihres
    0.18
    交易
    0.17
    '.$
    0.17
     입력
    0.17
     Ayuntamiento
    0.17
    ojs
    0.17
    /',
    0.16
     décrite
    0.16
     njih
    0.16
    POSITIVE LOGITS
    -
    0.19
    am
    0.18
    рет
    0.18
    nen
    0.18
    ong
    0.18
    راح
    0.18
    ening
    0.17
     Dig
    0.17
    aden
    0.17
    ysen
    0.17
    Activations Density 0.003%

    No Known Activations