© 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. 252380
    Prev
    Next
    INDEX
    Explanations

    Korean conversation

    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
     advancing
    1.08
    지는
    1.05
    진
    1.00
    져
    0.97
     जी
    0.95
     जि
    0.95
    지고
    0.91
     본
    0.91
    짐
    0.89
    졌
    0.88
    POSITIVE LOGITS
    صاب
    0.40
    गेड
    0.40
    puri
    0.39
     SBC
    0.38
     மிசோ
    0.37
     imgSrc
    0.37
     यो
    0.36
     効果
    0.36
    OMAS
    0.35
     மது
    0.35
    Activations Density 0.000%

    No Known Activations