© 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. 77469
    Prev
    Next
    INDEX
    Explanations

    ---

    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
     Marked
    0.39
     ns
    0.37
    atkar
    0.36
    凄
    0.36
    ႃ
    0.36
    }^{*}=
    0.35
    ursed
    0.35
     няко
    0.35
    คว
    0.34
     Acces
    0.34
    POSITIVE LOGITS
    Roy
    0.37
    мен
    0.37
    تا
    0.37
    مت
    0.36
    计
    0.36
    ⁣⁣
    0.36
     계
    0.35
    XIII
    0.35
    roy
    0.35
     KSI
    0.35
    Activations Density 0.001%

    No Known Activations