© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43724
    Prev
    Next
    INDEX
    Explanations

    systemic, latency, invasion

    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_13_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
    be
    0.60
     Allegheny
    0.53
    邑
    0.52
    as
    0.49
     enthous
    0.48
    ');
    0.46
    owel
    0.46
     Gestaltung
    0.46
    芴
    0.46
    '.
    0.45
    POSITIVE LOGITS
    𝒈
    0.55
     marches
    0.50
     тю
    0.50
     climates
    0.47
     arcade
    0.47
     topographic
    0.47
     mummy
    0.45
     metamorphic
    0.45
     tortor
    0.45
    цу
    0.45
    Activations Density 0.007%

    No Known Activations