© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164783
    Prev
    Next
    INDEX
    Explanations

    unitary matrices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
    id
    0.31
    urt
    0.28
    az
    0.27
    z
    0.27
    et
    0.27
    ate
    0.27
    iy
    0.27
    og
    0.26
    ge
    0.26
    ir
    0.26
    POSITIVE LOGITS
    ੴ
    0.22
     五
    0.22
     SIINFEKL
    0.21
     angustato
    0.20
     루트
    0.20
    第二个
    0.20
     beetroot
    0.20
     Bethany
    0.20
     Glycer
    0.20
     DAR
    0.20
    Activations Density 0.003%

    No Known Activations