© 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. 200568
    Prev
    Next
    INDEX
    Explanations

    two

    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
    মিন
    0.39
    OPT
    0.38
    PluginResult
    0.37
    คม
    0.37
     ಮಹ
    0.37
    measuredangle
    0.37
    ತ
    0.37
    を高
    0.36
    愤怒
    0.36
     মনোন
    0.36
    POSITIVE LOGITS
     /=
    0.40
    lou
    0.37
    heu
    0.37
     Wu
    0.37
     verbal
    0.36
    ltu
    0.36
     People
    0.36
    looped
    0.36
     He
    0.36
    vu
    0.35
    Activations Density 0.001%

    No Known Activations