© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198565
    Prev
    Next
    INDEX
    Explanations

    contemporary romance, erotic romance, FBI negotiation

    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_12_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
    Libraries
    0.55
    Profiler
    0.53
    Ber
    0.51
    大
    0.50
    Book
    0.50
    Library
    0.50
    バ
    0.49
    碣
    0.49
    βα
    0.49
    ma
    0.48
    POSITIVE LOGITS
     polyp
    0.55
     философ
    0.54
     resection
    0.51
     innovación
    0.51
     têm
    0.50
     cooperate
    0.50
     direção
    0.50
     philos
    0.50
     cooperation
    0.50
     multinational
    0.49
    Activations Density 0.003%

    No Known Activations