© 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. 213368
    Prev
    Next
    INDEX
    Explanations

    kl/cl sounds

    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
    Вакансия
    0.41
     پروت
    0.39
     Fractals
    0.38
    驍
    0.38
    ierre
    0.38
    PSA
    0.38
    sav
    0.37
    ธอ
    0.37
    হ্য
    0.37
     познакоми
    0.37
    POSITIVE LOGITS
     Kl
    1.25
     kl
    1.23
    Kl
    1.14
    kl
    0.99
     클
    0.82
     KL
    0.76
     cl
    0.75
    KL
    0.68
     klo
    0.65
     Cl
    0.64
    Activations Density 0.002%

    No Known Activations