© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118521
    Prev
    Next
    INDEX
    Explanations

    frequency twice rate

    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_27_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
    ();
    0.27
     okun
    0.26
     agregado
    0.25
     autocratic
    0.25
     interpreta
    0.25
     стре
    0.25
     itch
    0.25
     Mij
    0.25
    FBSDKError
    0.25
     प्रत
    0.24
    POSITIVE LOGITS
     parallèles
    0.31
     ramping
    0.31
     courbes
    0.28
    🥐
    0.28
     concernant
    0.28
     culminating
    0.28
    ഹന
    0.27
     regarding
    0.27
    radian
    0.27
     ujung
    0.27
    Activations Density 0.003%

    No Known Activations