© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81619
    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_0_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
    ле
    2.20
    the
    1.70
    تون
    1.50
    ל
    1.45
    z
    1.44
    მასრულ
    1.43
    л
    1.43
    sthe
    1.41
    ן
    1.41
    st
    1.40
    POSITIVE LOGITS
     steril
    1.41
     to
    1.31
     not
    1.22
     sensit
    1.19
    이지만
    1.19
     κάθε
    1.16
     crystall
    1.14
    การ
    1.13
    ")
    1.13
    aya
    1.11
    Activations Density 0.000%

    No Known Activations