© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85317
    Prev
    Next
    INDEX
    Explanations

    devices and technology

    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_23_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
    ._
    0.40
     Kenny
    0.40
     Morn
    0.39
     beings
    0.38
     kent
    0.38
     Gé
    0.37
     heartbroken
    0.37
     sik
    0.36
    sans
    0.36
     awn
    0.36
    POSITIVE LOGITS
    Synchronization
    0.44
    陀
    0.44
    𝒋
    0.41
     просто
    0.41
     পণ
    0.41
     ভাড়া
    0.40
     Synchronization
    0.40
    hora
    0.40
     ساختمان
    0.40
     раздра
    0.40
    Activations Density 0.000%

    No Known Activations