© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130670
    Prev
    Next
    INDEX
    Explanations

    empathetic, committed

    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_1_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
    ید
    1.64
    á
    1.32
    ной
    1.26
     as
    1.20
    ą
    1.09
    ə
    1.08
     and
    1.07
    یس
    1.05
    ೇ
    1.05
    기
    1.04
    POSITIVE LOGITS
    ).
    1.20
    ról
    1.13
    4
    1.05
     जिसकी
    0.90
    在
    0.90
    もら
    0.88
    тни
    0.88
    )...
    0.87
     যেটি
    0.87
    ،
    0.87
    Activations Density 0.001%

    No Known Activations