© 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
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 124548
    Prev
    Next
    INDEX
    Explanations

    graphical representation

    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_3_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
    dominated
    0.69
    d
    0.67
    ut
    0.63
     exposé
    0.61
    (
    0.60
     तैया
    0.60
    dicke
    0.59
    Beverungen
    0.59
    də
    0.58
     endowment
    0.57
    POSITIVE LOGITS
    อง
    0.69
     to
    0.66
    л
    0.65
    は
    0.63
     is
    0.60
    는
    0.60
    ל
    0.58
    ليه
    0.56
     you
    0.55
    न्त्री
    0.55
    Activations Density 0.000%

    No Known Activations