© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160833
    Prev
    Next
    INDEX
    Explanations

    ELI5

    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_2_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
     avaient
    1.23
     atentos
    1.16
    حی
    1.13
    amı
    1.10
    ਾ
    1.09
    醌
    1.09
     Пе
    1.09
    하는데
    1.09
     afirmó
    1.09
    の下
    1.05
    POSITIVE LOGITS
    d
    1.55
    st
    1.52
     for
    1.50
    m
    1.49
     as
    1.48
    ä
    1.46
    v
    1.41
    se
    1.41
     with
    1.37
    ns
    1.35
    Activations Density 0.001%

    No Known Activations