© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198113
    Prev
    Next
    INDEX
    Explanations

    nuances

    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_4_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
    k
    1.45
    v
    1.35
    ll
    1.34
     I
    1.29
    g
    1.29
    ↵
    1.17
    ni
    1.17
    n
    1.15
    nn
    1.13
    se
    1.13
    POSITIVE LOGITS
    ו
    1.45
    و
    1.43
    ু
    1.35
    ুল
    1.30
    ா
    1.23
    حي
    1.21
    ার
    1.20
    共に
    1.20
    ூ
    1.16
    ্রো
    1.16
    Activations Density 0.006%

    No Known Activations