© 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. 22686
    Prev
    Next
    INDEX
    Explanations

    `/**` comment start

    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
    യിലേ
    0.39
     ап
    0.34
    🩶
    0.33
     hollow
    0.33
    ীন
    0.33
     elixir
    0.33
     Ново
    0.33
     Dupree
    0.33
    >{{
    0.32
     repeat
    0.32
    POSITIVE LOGITS
    @
    0.48
    @(
    0.44
    deal
    0.41
    */
    0.38
    Supports
    0.38
    Sto
    0.38
    Support
    0.38
    meth
    0.38
    supports
    0.37
    Meth
    0.37
    Activations Density 0.000%

    No Known Activations