© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137105
    Prev
    Next
    INDEX
    Explanations

    URIs and prefixes

    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_37_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
    nmid
    0.52
     roar
    0.38
     stmt
    0.37
    жить
    0.37
    而
    0.35
     ಅಲ್ಲ
    0.35
     restaurants
    0.35
    aniach
    0.35
    ництва
    0.34
    aise
    0.34
    POSITIVE LOGITS
     $<\
    0.36
     Heading
    0.36
    țion
    0.36
     Datum
    0.35
    bras
    0.35
     Recording
    0.35
     Detalles
    0.35
     deten
    0.35
     revising
    0.35
     Fonseca
    0.35
    Activations Density 0.000%

    No Known Activations