© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120146
    Prev
    Next
    INDEX
    Explanations

    acquiring or demonstrating skills

    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
    ستہ
    0.45
    acamole
    0.42
    ற்
    0.39
    ις
    0.39
    :"+
    0.39
     ایسے
    0.39
    पाठी
    0.38
    म्मू
    0.36
    vorsch
    0.36
     اسلح
    0.36
    POSITIVE LOGITS
     Qd
    0.38
    No
    0.38
     PPE
    0.38
     அட
    0.37
    SIBLE
    0.37
    <div>
    0.36
    Cad
    0.35
     No
    0.34
    פט
    0.34
     prem
    0.34
    Activations Density 0.004%

    No Known Activations