© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85938
    Prev
    Next
    INDEX
    Explanations

    y = mx + b

    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_23_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
    빠
    0.44
    स्तेमाल
    0.44
    pct
    0.43
    ava
    0.39
    cant
    0.39
     अँ
    0.39
    poser
    0.38
    stap
    0.38
     birlikte
    0.38
    sponsored
    0.38
    POSITIVE LOGITS
    }$
    0.39
     цих
    0.38
     thoại
    0.38
     الصفحة
    0.38
     Visions
    0.37
     लाइन
    0.36
     നേരി
    0.36
     செய்க
    0.36
     ολο
    0.36
     confronti
    0.36
    Activations Density 0.001%

    No Known Activations