© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236936
    Prev
    Next
    INDEX
    Explanations

    education and graduation status

    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_25_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
    生涯
    0.42
     입력
    0.40
     antiv
    0.39
    არის
    0.39
     학
    0.39
     доба
    0.38
     საჭ
    0.37
    豌
    0.37
     유
    0.36
     전문
    0.36
    POSITIVE LOGITS
    افئ
    0.43
    Tips
    0.42
     mesmos
    0.41
     Tips
    0.41
    獰
    0.41
     serem
    0.40
    শের
    0.39
    mdp
    0.39
     Behind
    0.39
    તમાં
    0.38
    Activations Density 0.001%

    No Known Activations