© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227092
    Prev
    Next
    INDEX
    Explanations

    critical issue

    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_6_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
    t
    1.38
    is
    1.25
    on
    1.13
    ین
    1.01
    um
    1.00
    c
    1.00
    in
    0.96
    has
    0.95
    un
    0.93
    n
    0.93
    POSITIVE LOGITS
     be
    1.10
    ៤
    0.95
    ،
    0.93
    ，
    0.92
    。
    0.92
    ті
    0.91
    ۔
    0.91
     ৩
    0.88
    ³.
    0.85
    ۴
    0.85
    Activations Density 0.005%

    No Known Activations