© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168413
    Prev
    Next
    INDEX
    Explanations

    beginning stages

    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_34_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
     Previous
    0.43
     previous
    0.39
     cfg
    0.39
     पिछली
    0.38
    Previous
    0.38
     предыду
    0.37
     \$
    0.36
    صفر
    0.35
     barely
    0.35
     %(
    0.34
    POSITIVE LOGITS
     phase
    0.42
     EZ
    0.40
    phase
    0.40
    驗
    0.39
     toca
    0.39
     Hometown
    0.39
    phases
    0.38
    process
    0.37
     দ্বিতীয়
    0.37
     procesu
    0.36
    Activations Density 0.067%

    No Known Activations