© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214025
    Prev
    Next
    INDEX
    Explanations

    langchain or langson

    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
     I
    1.13
     (
    1.06
     Ś
    1.04
     QSO
    1.03
    !
    1.03
     V
    1.02
    ور
    1.01
    数据显示
    1.00
    狯
    1.00
     Scri
    1.00
    POSITIVE LOGITS
    ان
    1.61
     on
    1.45
    ین
    1.42
    on
    1.41
    ле
    1.38
    2
    1.38
     or
    1.31
    на
    1.28
    an
    1.24
    s
    1.23
    Activations Density 0.001%

    No Known Activations