© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 2502
    Prev
    Next
    INDEX
    Explanations

    actions and interaction

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     give
    2.13
    Give
    2.13
     Give
    2.08
    give
    2.03
     giving
    1.98
    給
    1.95
     gave
    1.85
    给
    1.84
     GIVE
    1.80
     gives
    1.78
    POSITIVE LOGITS
    elto
    0.38
    atos
    0.37
    ôi
    0.36
     相
    0.36
    齋
    0.35
    ظم
    0.35
    arithmic
    0.33
     ساي
    0.33
    setCurrent
    0.33
    삼
    0.33
    Activations Density 0.130%

    No Known Activations