© 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. 50092
    Prev
    Next
    INDEX
    Explanations

    meta

    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
    راح
    0.38
    猝
    0.37
    prison
    0.36
    дая
    0.35
    疥
    0.35
    Prison
    0.35
     কিন্ত
    0.34
    olefin
    0.34
    modal
    0.34
    ومت
    0.34
    POSITIVE LOGITS
    Clar
    0.49
     clarifying
    0.43
    スタンダード
    0.43
     Nam
    0.43
     nam
    0.42
     expressão
    0.40
    Ệ
    0.40
     synthes
    0.40
     Sinclair
    0.40
    stanza
    0.40
    Activations Density 0.001%

    No Known Activations