© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 102212
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    <unused26>
    0.46
     ねえ
    0.44
     विधेयक
    0.40
    gherita
    0.40
    <unused28>
    0.39
     তাস
    0.39
    뚤
    0.38
     prou
    0.38
     metri
    0.38
    openapi
    0.38
    POSITIVE LOGITS
    alm
    0.41
     ESP
    0.38
    こだ
    0.38
     шта
    0.37
     LM
    0.35
     alm
    0.35
    濵
    0.35
     esp
    0.34
    コナ
    0.34
    ੫
    0.34
    Activations Density 0.003%

    No Known Activations