© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205767
    Prev
    Next
    INDEX
    Explanations

    breaking the sound barrier

    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_37_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
     Ur
    0.38
     milestones
    0.38
     वोल्
    0.38
     alterar
    0.37
    Volt
    0.36
    ྭ
    0.35
    ğlu
    0.35
     शिखर
    0.34
    ленными
    0.34
     Resistance
    0.34
    POSITIVE LOGITS
     stiffer
    0.52
     stiffness
    0.45
     stiff
    0.43
     เอ
    0.41
    shear
    0.41
     shear
    0.40
     Stiffness
    0.40
    騒
    0.37
    海水
    0.37
     sounded
    0.36
    Activations Density 0.000%

    No Known Activations