© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138440
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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_46_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
     figure
    0.47
    figure
    0.43
    uction
    0.40
     seven
    0.38
    
    0.38
     delinqu
    0.38
     כמה
    0.38
     ANOTHER
    0.37
     MPI
    0.37
     ثلاثه
    0.37
    POSITIVE LOGITS
    正
    0.42
    Operator
    0.40
    operator
    0.39
    เขา
    0.38
     그는
    0.38
    positive
    0.38
     yath
    0.38
    Elements
    0.37
    şık
    0.37
    Each
    0.36
    Activations Density 0.004%

    No Known Activations