© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27550
    Prev
    Next
    INDEX
    Explanations

    executing SQL commands

    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_10_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
     inhibitor
    0.64
     as
    0.63
    ⵕ
    0.62
     squats
    0.61
     redshifts
    0.60
     schemas
    0.59
    𝚆
    0.57
     cycles
    0.57
     discontinuities
    0.57
    '
    0.56
    POSITIVE LOGITS
    on
    0.74
    at
    0.73
    s
    0.66
    até
    0.65
    encija
    0.65
    ים
    0.62
    сан
    0.61
    0
    0.60
    ς
    0.58
    andt
    0.56
    Activations Density 0.000%

    No Known Activations