© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60503
    Prev
    Next
    INDEX
    Explanations

    explaining or resolving problems

    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_11_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
     pins
    0.59
     vines
    0.57
     knuckles
    0.49
    畚
    0.48
     altitudes
    0.47
     capsules
    0.46
     wins
    0.46
    ர்கள்
    0.46
     jerseys
    0.46
     axons
    0.46
    POSITIVE LOGITS
    c
    0.51
    position
    0.50
    getServer
    0.49
     counteract
    0.49
    cause
    0.48
    prefer
    0.48
    tried
    0.48
    preserve
    0.48
    compound
    0.47
    present
    0.47
    Activations Density 0.000%

    No Known Activations