© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88605
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    in
    1.16
    er
    0.91
    ли
    0.91
    o
    0.70
    al
    0.70
    that
    0.67
    eron
    0.67
    erat
    0.67
    an
    0.66
    ungu
    0.66
    POSITIVE LOGITS
    dı
    0.77
    dır
    0.75
    𝒔
    0.71
    دی
    0.68
    یس
    0.68
     curators
    0.66
    𝒅
    0.66
    də
    0.66
     tremendous
    0.65
    یم
    0.64
    Activations Density 0.000%

    No Known Activations