© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208943
    Prev
    Next
    INDEX
    Explanations

    building completion dates

    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_20_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
     lancéolées
    0.45
    PerTrial
    0.43
    翦
    0.43
    下方
    0.43
    عند
    0.41
    ডির
    0.41
     stellt
    0.41
    క్కి
    0.41
    fted
    0.40
    笞
    0.40
    POSITIVE LOGITS
    ba
    0.46
    ing
    0.45
    ---
    0.44
     communication
    0.44
    wick
    0.43
     biotechn
    0.43
     ba
    0.42
     proficiency
    0.42
     ,
    0.42
    wa
    0.42
    Activations Density 0.000%

    No Known Activations