© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2956
    Prev
    Next
    INDEX
    Explanations

    units with exponents or powers

    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_40_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
    Instituto
    0.38
     Erasmus
    0.37
     அழ
    0.36
    ।*
    0.36
    欢
    0.35
     Lust
    0.34
    skl
    0.34
     establece
    0.34
     conveys
    0.34
    𒍑
    0.34
    POSITIVE LOGITS
    ²
    0.81
    ²)
    0.74
    ².
    0.68
    ²,
    0.67
    ²+
    0.63
    ²',
    0.63
    ³
    0.62
    ²/
    0.58
    ³)
    0.56
     Squared
    0.55
    Activations Density 0.072%

    No Known Activations