© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206316
    Prev
    Next
    INDEX
    Explanations

    pre

    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
     exposes
    0.44
     T
    0.42
     t
    0.41
     einges
    0.41
     trained
    0.40
     k
    0.40
     Trained
    0.39
     training
    0.39
     esp
    0.39
     Distributors
    0.38
    POSITIVE LOGITS
    Pre
    0.41
    Mask
    0.39
     Pre
    0.39
     served
    0.38
    ș
    0.38
    Reached
    0.38
    ß
    0.38
    BinaryOperation
    0.38
    Reduction
    0.38
     उपसर्ग
    0.38
    Activations Density 0.002%

    No Known Activations