© 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. 68874
    Prev
    Next
    INDEX
    Explanations

    arm

    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
    Big
    0.42
     Goldman
    0.40
     affected
    0.38
    ōu
    0.37
     MSc
    0.37
    ammers
    0.35
    妹
    0.35
     Big
    0.34
     dressing
    0.34
    atenate
    0.34
    POSITIVE LOGITS
     колек
    0.42
    賀
    0.41
     tumble
    0.40
     Guill
    0.38
     ajouter
    0.38
     Hild
    0.37
     коллек
    0.36
    淑
    0.36
     maximale
    0.36
    佾
    0.36
    Activations Density 0.001%

    No Known Activations