© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176478
    Prev
    Next
    INDEX
    Explanations

    Nature

    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_50_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
    ರಿಯ
    0.40
    Œ
    0.37
     бре
    0.37
     بشر
    0.35
    不定
    0.34
    arsenic
    0.34
    ภั
    0.34
    .//
    0.34
    ipient
    0.34
    oliko
    0.34
    POSITIVE LOGITS
    ▔
    0.43
     systemat
    0.43
    สัน
    0.39
     Locals
    0.38
     lf
    0.38
     Mains
    0.38
     pubblico
    0.38
     Sanford
    0.38
    نما
    0.38
    橥
    0.38
    Activations Density 0.000%

    No Known Activations