© 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. 54292
    Prev
    Next
    INDEX
    Explanations

    joints and movement

    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
     precedence
    0.38
    }));
    0.36
    ifiques
    0.36
     দেব
    0.35
     temper
    0.35
    ✰
    0.35
    arkan
    0.34
    affected
    0.34
    authenticated
    0.34
    abol
    0.34
    POSITIVE LOGITS
     нагрузки
    0.52
    臀
    0.44
     reinforcements
    0.41
     artic
    0.41
    Seconds
    0.40
    돔
    0.39
     Specialty
    0.39
     load
    0.39
     transfert
    0.38
     scrolling
    0.38
    Activations Density 0.006%

    No Known Activations