© 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. 215346
    Prev
    Next
    INDEX
    Explanations

    dirección and related words

    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
    е
    1.53
    ل
    1.51
    t
    1.50
    ל
    1.45
     on
    1.38
    고
    1.38
    и
    1.30
    ان
    1.23
    ર
    1.21
    ח
    1.13
    POSITIVE LOGITS
    '।
    1.09
    )’
    1.06
    дный
    1.05
    deki
    1.03
    ный
    1.01
     která
    1.00
     který
    0.98
    ።
    0.97
    ೇ
    0.97
    )
    0.96
    Activations Density 0.000%

    No Known Activations