© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3763
    Prev
    Next
    INDEX
    Explanations

    file paths and types

    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_39_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
    Adjustment
    0.32
     компет
    0.31
    헴
    0.30
    <0xD8>
    0.29
    Compet
    0.29
    արդ
    0.28
    Escolh
    0.28
     компетен
    0.27
    壶
    0.27
    Compat
    0.27
    POSITIVE LOGITS
     So
    0.36
    ily
    0.35
     workplaces
    0.34
     EBS
    0.33
     workplace
    0.32
     Wo
    0.31
     crave
    0.30
    ubhav
    0.30
    ube
    0.30
    So
    0.29
    Activations Density 0.000%

    No Known Activations