© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210278
    Prev
    Next
    INDEX
    Explanations

    stronger than you think

    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_43_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
     laps
    0.38
    ᱽ
    0.35
    <0xB0>
    0.35
     Jasmine
    0.34
     unabhäng
    0.34
    Rl
    0.34
     முடியாது
    0.33
     ماشینونو
    0.33
     accomplished
    0.33
     chast
    0.33
    POSITIVE LOGITS
    ENER
    0.40
    кр
    0.38
    BUF
    0.38
     فصل
    0.38
     biologie
    0.37
    Kap
    0.37
     Turbo
    0.37
    庚
    0.37
    kap
    0.36
    ORDER
    0.36
    Activations Density 0.000%

    No Known Activations