© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139284
    Prev
    Next
    INDEX
    Explanations

    items or methods

    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
    㦣
    0.45
     Wax
    0.40
     douloureuse
    0.40
     comunic
    0.40
    Fade
    0.39
    痛
    0.39
     வந்தால்
    0.38
     waxed
    0.37
     dets
    0.37
     fading
    0.37
    POSITIVE LOGITS
     ishlab
    0.39
    mel
    0.37
    召
    0.36
    Proc
    0.36
     മുത
    0.36
     irrit
    0.36
    ̳
    0.35
    رافی
    0.35
     Proc
    0.35
     Belong
    0.35
    Activations Density 0.082%

    No Known Activations