© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75005
    Prev
    Next
    INDEX
    Explanations

    Wait for synchronization

    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_31_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
    燐
    0.43
     рост
    0.39
     verificación
    0.39
     wzrost
    0.39
    checkFor
    0.37
    ቹን
    0.37
     себя
    0.36
    ⎢
    0.36
    Hung
    0.36
     renversement
    0.35
    POSITIVE LOGITS
     input
    0.40
     day
    0.38
     patch
    0.38
     Oracle
    0.37
     Kappa
    0.36
     herbal
    0.36
     freely
    0.35
     responsive
    0.35
     waved
    0.35
     gonf
    0.35
    Activations Density 0.003%

    No Known Activations