© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1572
    Prev
    Next
    INDEX
    Explanations

    wave phenomena and properties

    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_39_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
     ዘዴ
    0.42
     Kauff
    0.40
    гран
    0.38
     objeto
    0.38
    物の
    0.38
     vole
    0.38
    $\--
    0.37
    }})\
    0.37
     nitrite
    0.36
     radiolysis
    0.35
    POSITIVE LOGITS
     wave
    0.48
     wavefront
    0.47
     waves
    0.47
     oscillating
    0.44
     Envelope
    0.44
     traveling
    0.43
    wave
    0.43
     whist
    0.42
     Wave
    0.42
     wig
    0.42
    Activations Density 0.100%

    No Known Activations