© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211490
    Prev
    Next
    INDEX
    Explanations

    yelling or shouting

    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_19_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
    news
    0.40
    true
    0.38
    scheduled
    0.37
    ow
    0.36
    right
    0.36
    Ryan
    0.35
     остан
    0.35
    양
    0.35
    compass
    0.35
    ubern
    0.35
    POSITIVE LOGITS
     torsional
    0.47
     axially
    0.44
     frictional
    0.43
     Membrane
    0.43
     acetaldehyde
    0.40
    鈾
    0.40
     transmembrane
    0.40
     Struktur
    0.39
     initiale
    0.39
    胝
    0.39
    Activations Density 0.004%

    No Known Activations