© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227738
    Prev
    Next
    INDEX
    Explanations

    tùy thuộc/theo

    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_6_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
     be
    0.45
     publicité
    0.42
    ﻻ
    0.41
    ון
    0.39
    ัน
    0.38
     heeft
    0.38
     bảo
    0.38
     cóm
    0.38
     livré
    0.38
    َيْ
    0.37
    POSITIVE LOGITS
    larının
    0.51
    nd
    0.44
    lar
    0.43
    ne
    0.43
    number
    0.43
    nummer
    0.42
    this
    0.41
    n
    0.40
    src
    0.40
    lt
    0.39
    Activations Density 0.000%

    No Known Activations