© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43847
    Prev
    Next
    INDEX
    Explanations

    structures and definitions

    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_22_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
     adimensional
    0.45
     Woche
    0.44
     столи
    0.42
     miesią
    0.41
    뿅
    0.41
     rewarded
    0.41
     Groß
    0.41
     Slav
    0.41
     höher
    0.41
     später
    0.40
    POSITIVE LOGITS
    RECT
    0.46
     接
    0.45
     about
    0.45
    什么是
    0.43
    commonly
    0.43
     வி
    0.42
    oper
    0.42
     तथ्यों
    0.42
    formed
    0.42
    umas
    0.41
    Activations Density 0.000%

    No Known Activations