© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53507
    Prev
    Next
    INDEX
    Explanations

    low

    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_55_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
     Petrol
    0.42
    ﾔ
    0.40
     LD
    0.39
     lifestyle
    0.39
     Kow
    0.39
     Enth
    0.39
     कंट
    0.39
     Eating
    0.39
     memory
    0.38
     lifestyles
    0.38
    POSITIVE LOGITS
     obrig
    0.43
    revoke
    0.38
    buttonLevel
    0.38
    ेशनल
    0.38
    Organiz
    0.38
    rewrite
    0.37
     الأرض
    0.36
    __/
    0.36
    sidebar
    0.36
    帏
    0.36
    Activations Density 0.001%

    No Known Activations