© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195300
    Prev
    Next
    INDEX
    Explanations

    data access

    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_4_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
    ين
    0.84
     utilisent
    0.79
     `:`,
    0.75
     (
    0.75
    er
    0.75
    ಮ
    0.75
    ratto
    0.74
    heiro
    0.73
     ή
    0.73
     ಹಾಗೂ
    0.72
    POSITIVE LOGITS
    2
    1.09
    q
    0.92
    to
    0.90
    de
    0.88
    0
    0.85
    m
    0.77
    z
    0.76
    f
    0.75
    of
    0.74
    ار
    0.73
    Activations Density 0.001%

    No Known Activations