© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228337
    Prev
    Next
    INDEX
    Explanations

    addresses and names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    OCATION
    0.43
     ছাত্রলীগ
    0.37
    TOF
    0.36
     মোটা
    0.36
    Herz
    0.36
     वान
    0.36
    $-[
    0.36
    觉得
    0.35
    стане
    0.35
    uticas
    0.35
    POSITIVE LOGITS
     eye
    0.39
     seer
    0.39
     sov
    0.38
     role
    0.38
     scene
    0.38
    Ը
    0.38
     phrase
    0.37
     hele
    0.37
     gim
    0.37
     dgn
    0.37
    Activations Density 0.004%

    No Known Activations