© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39139
    Prev
    Next
    INDEX
    Explanations

    numbers and chart

    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
    0
    0.75
    ج
    0.69
    지
    0.68
    ه
    0.65
     komme
    0.63
    <0x80>
    0.61
     imm
    0.61
    Y
    0.61
     जिसमे
    0.61
    。
    0.61
    POSITIVE LOGITS
    в
    0.88
    ви
    0.87
    р
    0.82
    торой
    0.79
    𝚖
    0.77
    т
    0.75
    м
    0.73
    edges
    0.73
    င်
    0.70
    서
    0.70
    Activations Density 0.009%

    No Known Activations