© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199273
    Prev
    Next
    INDEX
    Explanations

    nginx configurations

    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_12_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
    彙
    0.63
    🥑
    0.59
     posisi
    0.58
     হুগলীর
    0.58
    ність
    0.56
     পরিস্থিত
    0.55
     Chí
    0.55
     হইত
    0.55
     Sicherheit
    0.54
     luogo
    0.53
    POSITIVE LOGITS
    g
    0.67
    ع
    0.62
    ka
    0.58
    eder
    0.58
    ge
    0.54
    gres
    0.54
    de
    0.53
    j
    0.51
    ga
    0.50
    durch
    0.49
    Activations Density 0.011%

    No Known Activations