© 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. 12844
    Prev
    Next
    INDEX
    Explanations

    reasoning and benchmarks

    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
     partial
    1.27
    partial
    1.22
     Partial
    1.22
    Partial
    1.16
     parcial
    0.99
     partielle
    0.80
    partials
    0.77
    ∂
    0.67
     partially
    0.66
     ∂
    0.66
    POSITIVE LOGITS
     Information
    0.49
    Information
    0.42
     information
    0.39
     biology
    0.38
     grade
    0.38
     PIR
    0.37
    iente
    0.37
     Account
    0.37
     इंफॉर्मेशन
    0.37
     accountants
    0.36
    Activations Density 0.036%

    No Known Activations