© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82579
    Prev
    Next
    INDEX
    Explanations

    shall

    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_53_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
    ilot
    0.38
     CHAN
    0.38
    ضع
    0.37
    actic
    0.36
     راس
    0.36
    જ
    0.35
     estuary
    0.34
    ージェ
    0.34
     孔
    0.34
     communs
    0.34
    POSITIVE LOGITS
    yte
    0.44
    Autoresizing
    0.42
     হলেও
    0.40
    árez
    0.40
    Action
    0.39
     asymmetries
    0.39
    ता
    0.38
    पणे
    0.38
    ním
    0.38
    lovens
    0.38
    Activations Density 0.000%

    No Known Activations