© 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. 211427
    Prev
    Next
    INDEX
    Explanations

    body parts muscles

    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
     heavily
    0.41
    Mike
    0.39
    校
    0.38
     校
    0.37
    vacancy
    0.36
     Aguilera
    0.36
     frequented
    0.36
     रिली
    0.36
    Reed
    0.36
    城
    0.36
    POSITIVE LOGITS
     polytopes
    0.40
     Medicina
    0.39
    onaut
    0.38
     médecine
    0.38
    stArray
    0.38
     RG
    0.37
     progen
    0.37
     medic
    0.37
    idung
    0.36
    RG
    0.36
    Activations Density 0.002%

    No Known Activations