© 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. 136423
    Prev
    Next
    INDEX
    Explanations

    principles and concepts

    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
     تلف
    0.54
    نت
    0.53
     Genn
    0.52
     Impro
    0.51
     दोहरा
    0.50
     Gases
    0.50
    sant
    0.50
    㣱
    0.50
    шни
    0.49
    бари
    0.49
    POSITIVE LOGITS
    at
    0.79
    ive
    0.52
     jau
    0.49
     പറ്റ
    0.49
    is
    0.49
     work
    0.49
     doğ
    0.49
    ule
    0.48
    ime
    0.48
    isable
    0.48
    Activations Density 0.000%

    No Known Activations