© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107320
    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_2_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
    al
    1.50
    re
    1.34
    ن
    1.34
    ch
    1.17
    el
    1.11
    anın
    1.11
    ad
    1.10
    ן
    1.08
    enar
    1.05
    il
    1.01
    POSITIVE LOGITS
    ä
    1.34
    AY
    1.16
    AI
    1.16
    8
    1.15
    ā
    1.14
    ка
    1.13
    EE
    1.12
    ان
    1.06
    ı
    1.06
    し
    1.03
    Activations Density 0.000%

    No Known Activations