© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4890
    Prev
    Next
    INDEX
    Explanations

    seaborn import

    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
     Pilar
    0.41
     percentages
    0.38
     PIL
    0.38
     coeff
    0.38
    PIL
    0.38
     {%
    0.37
     Atatürk
    0.37
     AVERAGE
    0.37
     inflamm
    0.36
    coeff
    0.36
    POSITIVE LOGITS
    套
    0.37
     Diaz
    0.36
    Diaz
    0.36
    Clean
    0.36
     диа
    0.35
     gato
    0.35
     Faun
    0.34
    seal
    0.34
     diaz
    0.34
     தூசி
    0.34
    Activations Density 0.015%

    No Known Activations