© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211101
    Prev
    Next
    INDEX
    Explanations

    khỏe không?, khoảng, ://

    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_5_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
    agamanam
    1.40
    =");
    1.21
    folds
    1.16
    is
    1.14
    hj
    1.14
    ahanga
    1.11
    kast
    1.08
    informed
    1.07
    latt
    1.07
    bahan
    1.06
    POSITIVE LOGITS
    .
    1.69
     in
    1.46
    י
    1.38
     que
    1.32
    ุ
    1.32
    ي
    1.27
     time
    1.26
     world
    1.20
     في
    1.19
    ين
    1.15
    Activations Density 0.000%

    No Known Activations