© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121295
    Prev
    Next
    INDEX
    Explanations

    website, image, model, receiver, technique, team, project, compiler, key

    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_27_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
    提供了
    0.39
     wê
    0.35
     gj
    0.35
    逸
    0.35
     terminated
    0.34
     adjunction
    0.34
     dah
    0.34
    ︡
    0.34
     충분
    0.34
     cigar
    0.33
    POSITIVE LOGITS
    drive
    0.42
     Sorg
    0.39
     मैं
    0.39
     Signs
    0.39
    crypt
    0.38
     एबी
    0.38
    nYou
    0.37
     मैंने
    0.36
     ನಾನು
    0.36
    nThe
    0.36
    Activations Density 0.001%

    No Known Activations