© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35400
    Prev
    Next
    INDEX
    Explanations

    low-code / low-light

    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_3_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
    mö
    0.70
    mär
    0.61
    bins
    0.58
    mark
    0.56
    bits
    0.56
    power
    0.55
    龍
    0.55
    gene
    0.54
    lane
    0.53
    parsing
    0.53
    POSITIVE LOGITS
    т
    0.77
    е
    0.71
    ات
    0.68
     cambi
    0.68
     prong
    0.68
    :
    0.66
    ی
    0.66
    ле
    0.65
    ‘
    0.65
    s
    0.64
    Activations Density 0.021%

    No Known Activations