© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118869
    Prev
    Next
    INDEX
    Explanations

    file operation and management

    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_27_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
    írez
    0.38
    ận
    0.37
    gerät
    0.36
     รู้
    0.34
    abhäng
    0.34
    qld
    0.33
    <0x9D>
    0.33
    elä
    0.33
    लीवुड
    0.32
    lod
    0.32
    POSITIVE LOGITS
     corros
    0.41
     infusions
    0.40
     aton
    0.39
     skyline
    0.38
     getline
    0.38
     humus
    0.38
     strengthen
    0.38
     갖
    0.38
    人性
    0.38
    🄰
    0.38
    Activations Density 0.001%

    No Known Activations