© 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. 210554
    Prev
    Next
    INDEX
    Explanations

    words around Bedikat Chametz

    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
    る
    1.42
    of
    1.16
    ו
    1.13
    ာ
    1.13
    تان
    1.12
    the
    1.08
    ள்
    1.08
    ד
    1.08
    고
    1.03
    ம்
    1.02
    POSITIVE LOGITS
     llegó
    1.02
    리
    1.02
     Prisma
    0.99
     abstra
    0.97
    క్కువ
    0.95
     PUBG
    0.95
    n
    0.95
     Alicante
    0.93
     jednotliv
    0.91
    IOT
    0.90
    Activations Density 0.000%

    No Known Activations