© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202368
    Prev
    Next
    INDEX
    Explanations

    concerns

    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_46_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
    BeginInit
    0.41
    渙
    0.41
     poput
    0.39
    ”),
    0.38
    cnty
    0.37
    ."),
    0.37
     вод
    0.36
     가능하다
    0.36
     Whi
    0.34
    狀
    0.34
    POSITIVE LOGITS
    ᴸ
    0.43
    建议
    0.41
    GetString
    0.40
     Suggestions
    0.40
     suggestions
    0.39
     addressed
    0.39
    涉及
    0.39
     adress
    0.38
     address
    0.38
     adresu
    0.38
    Activations Density 0.001%

    No Known Activations