© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76383
    Prev
    Next
    INDEX
    Explanations

    causes or contributes

    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_31_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
    adjust
    0.27
    ole
    0.26
    ictures
    0.26
     adjusts
    0.26
    scales
    0.26
    调整
    0.26
     adjusting
    0.26
    蔦
    0.26
    racial
    0.25
    社会主义
    0.25
    POSITIVE LOGITS
     इक
    0.29
     fel
    0.28
    িনের
    0.27
     "]
    0.27
     berupa
    0.26
    Fel
    0.26
    厥
    0.26
     ferr
    0.25
    などが
    0.25
    差点
    0.25
    Activations Density 0.013%

    No Known Activations