© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234940
    Prev
    Next
    INDEX
    Explanations

    modelmodel of

    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_32_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
     팬
    0.52
     projek
    0.48
    开源
    0.45
     fan
    0.45
     websites
    0.43
     Projek
    0.43
     అభిమా
    0.43
    Fan
    0.43
     Websites
    0.43
     нео
    0.42
    POSITIVE LOGITS
    幹
    0.42
    证
    0.37
     Bourgoin
    0.36
     sticks
    0.36
    enk
    0.36
     chic
    0.35
    iqueness
    0.35
    챱
    0.35
    ramatta
    0.35
    ick
    0.34
    Activations Density 0.033%

    No Known Activations