© 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. 159888
    Prev
    Next
    INDEX
    Explanations

    gravitational waves

    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
    "
    2.23
    '
    2.02
    (
    1.53
    ↵
    1.48
    a
    1.48
    i
    1.37
    :
    1.30
    h
    1.30
    )
    1.18
    -
    1.17
    POSITIVE LOGITS
    на
    1.31
    తో
    1.10
    مكن
    1.10
    х
    1.09
    مون
    1.05
    مس
    0.95
    مي
    0.95
    人
    0.94
    ть
    0.93
    وں
    0.93
    Activations Density 0.000%

    No Known Activations