© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 704
    Prev
    Next
    INDEX
    Explanations

    Nova Blast

    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_40_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
     dense
    0.43
    dense
    0.43
     Dense
    0.40
    Dense
    0.39
     длина
    0.39
    pur
    0.38
    cule
    0.37
    췄
    0.36
    matt
    0.36
    슨
    0.35
    POSITIVE LOGITS
    秇
    0.44
    templatemo
    0.41
    权限
    0.38
     tags
    0.37
     Holiday
    0.37
     Hez
    0.36
    ति
    0.36
    FileUpload
    0.35
     vati
    0.35
    嗬
    0.35
    Activations Density 0.042%

    No Known Activations