© 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. 232736
    Prev
    Next
    INDEX
    Explanations

    purposes

    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
     Strictly
    0.44
     ٹوٹ
    0.43
    厳
    0.41
    Strict
    0.41
     وتن
    0.39
     immunoglobulin
    0.39
     strictly
    0.38
    严格
    0.38
    咨询
    0.38
    Modified
    0.37
    POSITIVE LOGITS
     billy
    0.41
     Кали
    0.39
    리티
    0.38
     thisTrial
    0.38
     पढ
    0.37
     Weltkrieg
    0.37
     guilds
    0.37
    鉗
    0.37
    نر
    0.36
    (`<
    0.36
    Activations Density 0.000%

    No Known Activations