© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194579
    Prev
    Next
    INDEX
    Explanations

    Maria or killed

    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_4_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
    ן
    1.54
    اء
    1.24
    म
    1.17
    ם
    1.14
    ס
    1.12
    회
    1.00
    د
    0.99
    린
    0.99
    うまく
    0.98
    m
    0.98
    POSITIVE LOGITS
    ke
    1.00
    ka
    0.91
    OL
    0.91
    AV
    0.90
    IN
    0.89
    ien
    0.88
    AN
    0.86
     lä
    0.85
    ig
    0.84
     as
    0.82
    Activations Density 0.001%

    No Known Activations