© 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. 81787
    Prev
    Next
    INDEX
    Explanations

    semicolon

    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
     περι
    0.38
    yclerView
    0.37
    دە
    0.35
     adiab
    0.35
     CORPER
    0.35
     ory
    0.35
    ο
    0.35
     Ó
    0.34
    tv
    0.34
     saludable
    0.34
    POSITIVE LOGITS
     नक्सलियों
    0.38
    čních
    0.38
    atoren
    0.36
    耖
    0.35
    ocardial
    0.34
    čním
    0.34
     Cases
    0.34
    митри
    0.33
    }[!
    0.33
    жник
    0.33
    Activations Density 0.013%

    No Known Activations