© 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. 201277
    Prev
    Next
    INDEX
    Explanations

    weightlifting

    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
    ature
    0.59
    ä
    0.56
     Wilbur
    0.55
     Edmund
    0.54
    agas
    0.54
     Ember
    0.52
    atura
    0.52
    ádio
    0.51
    endtime
    0.51
    anda
    0.50
    POSITIVE LOGITS
     scrot
    0.57
     commits
    0.54
     organizes
    0.54
    ك
    0.54
     leverages
    0.53
     tableView
    0.52
     setResult
    0.52
    ול
    0.51
     trusts
    0.51
     achieves
    0.51
    Activations Density 0.000%

    No Known Activations