© 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. 2809
    Prev
    Next
    INDEX
    Explanations

    transparent color or background

    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
    汁
    0.45
     improve
    0.40
     Soup
    0.40
     Southport
    0.40
    pieza
    0.40
    improve
    0.40
     terapia
    0.39
     nerv
    0.38
     chem
    0.38
     io
    0.38
    POSITIVE LOGITS
    Transparent
    0.59
     transparent
    0.57
     прозра
    0.54
    transparent
    0.53
     블랙
    0.53
    黒
    0.52
    Black
    0.51
     black
    0.51
     BLACK
    0.51
    黑色
    0.51
    Activations Density 0.004%

    No Known Activations