© 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. 121115
    Prev
    Next
    INDEX
    Explanations

    stop or end

    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
    ەند
    0.44
     tiêu
    0.40
     extinguished
    0.40
    𝕤
    0.40
     desaparecer
    0.40
     consensual
    0.39
    消
    0.39
     डिपॉ
    0.38
    getCamera
    0.37
    ಟ್
    0.37
    POSITIVE LOGITS
     мяс
    0.38
     наре
    0.37
     equalities
    0.37
     Rap
    0.36
    蟒
    0.35
     עד
    0.35
    Ự
    0.35
    に戻
    0.33
     पहना
    0.33
     EARL
    0.33
    Activations Density 0.009%

    No Known Activations