© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222624
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    akarane
    0.55
    偻
    0.50
    umlahan
    0.49
    funktionen
    0.48
     ويمكن
    0.46
    MathOperator
    0.46
    ylmethylsulfanyl
    0.45
    rums
    0.45
    栱
    0.45
    ken
    0.45
    POSITIVE LOGITS
     cheques
    0.57
     feudal
    0.53
     variety
    0.52
    ﻪ
    0.52
     vídeos
    0.51
     trai
    0.50
     way
    0.50
     notify
    0.49
    Н
    0.49
     depth
    0.49
    Activations Density 0.000%

    No Known Activations