© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157588
    Prev
    Next
    INDEX
    Explanations

    Twinkle Twinkle Little Star

    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
    s
    1.47
    the
    1.46
    й
    1.45
    т
    1.41
    य
    1.30
    y
    1.28
    지
    1.26
    u
    1.25
    k
    1.20
    ग
    1.20
    POSITIVE LOGITS
    1.55
    ัน
    1.23
    、
    1.16
    在
    1.10
    ט
    1.07
    もら
    1.06
    も
    1.05
    ও
    1.04
    ’
    0.96
    områ
    0.95
    Activations Density 0.001%

    No Known Activations