© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201619
    Prev
    Next
    INDEX
    Explanations

    production runs

    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
    ai
    0.46
    set
    0.46
    Field
    0.45
    ca
    0.43
     {
    0.42
    European
    0.42
    思
    0.42
    yle
    0.41
    CA
    0.41
    AL
    0.41
    POSITIVE LOGITS
    ią
    0.51
     Polaroid
    0.49
     கேட்க
    0.48
    يء
    0.48
     tunes
    0.46
     polos
    0.46
    ologías
    0.46
    <bbox>
    0.46
    ঙে
    0.45
     demol
    0.44
    Activations Density 0.000%

    No Known Activations