© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13765
    Prev
    Next
    INDEX
    Explanations

    manifest.json for chrome extensions

    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_40_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
    Paf
    0.42
    াদিত
    0.41
    詄
    0.40
     Zw
    0.38
    MESH
    0.38
     annotation
    0.38
     हिस्ट्री
    0.38
    objs
    0.37
    扦
    0.37
     кури
    0.37
    POSITIVE LOGITS
    profile
    0.41
    he
    0.39
    hi
    0.39
     ডা
    0.38
    body
    0.38
     panic
    0.38
    yb
    0.36
     alarms
    0.36
    terraform
    0.36
    out
    0.35
    Activations Density 0.004%

    No Known Activations