© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217199
    Prev
    Next
    INDEX
    Explanations

    say explicit

    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_50_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
     Enum
    0.42
    اری
    0.40
     issue
    0.39
     booth
    0.38
     Petrus
    0.37
     tweeter
    0.36
     Esse
    0.36
    ﻫ
    0.36
    issue
    0.36
    镙
    0.36
    POSITIVE LOGITS
    jac
    0.44
    ABD
    0.41
    Your
    0.39
     Reihen
    0.38
    NotFound
    0.38
    onden
    0.38
     вашего
    0.38
    Jac
    0.37
     ziehen
    0.37
    สิ้น
    0.37
    Activations Density 0.003%

    No Known Activations