© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242434
    Prev
    Next
    INDEX
    Explanations

    citations and numbers

    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_40_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
     мате
    0.34
     Covering
    0.34
    俄
    0.33
    Logout
    0.32
    fourth
    0.32
    haust
    0.31
    Gr
    0.31
     cobert
    0.31
    hlt
    0.31
     fourteenth
    0.30
    POSITIVE LOGITS
    䒷
    0.37
     hyperplasia
    0.37
    맺
    0.36
     ब्रेन
    0.36
     routed
    0.35
     zeggen
    0.34
    რივი
    0.34
    یتی
    0.34
     spricht
    0.34
     expedi
    0.34
    Activations Density 0.000%

    No Known Activations