© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208487
    Prev
    Next
    INDEX
    Explanations

    substances and ingredients

    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_56_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
     agenda
    0.39
    成交
    0.39
    事物
    0.39
    勇
    0.38
    教科
    0.38
    thisComponent
    0.37
     assets
    0.36
    াজিক
    0.36
     charter
    0.35
    emeinschaft
    0.35
    POSITIVE LOGITS
     sauce
    0.77
     powder
    0.67
     rods
    0.65
     stones
    0.64
    汁
    0.64
     पाउडर
    0.63
     disease
    0.60
     oxide
    0.59
    salad
    0.59
     juice
    0.59
    Activations Density 0.119%

    No Known Activations