© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106651
    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_1_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
    v
    1.27
     at
    1.05
     of
    1.02
    mith
    1.02
     on
    1.01
     to
    1.00
    ن
    1.00
    uelle
    0.98
    mik
    0.98
    mw
    0.96
    POSITIVE LOGITS
    ка
    2.08
    も
    1.44
    在
    1.41
     mesmer
    1.38
    де
    1.34
    да
    1.33
    ы
    1.32
    га
    1.29
    να
    1.28
    도
    1.27
    Activations Density 0.000%

    No Known Activations