© 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-3-4B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245938
    Prev
    Next
    INDEX
    Explanations

    breakdown or title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_11_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
     ambassador
    1.02
     período
    0.98
     அல்லது
    0.96
    逺
    0.94
     submarine
    0.94
     sturdy
    0.94
     outpost
    0.92
     placas
    0.91
     north
    0.90
     arrested
    0.90
    POSITIVE LOGITS
     Leicht
    0.75
    シス
    0.69
    ղ
    0.67
     Analysis
    0.65
    াশ
    0.64
     Colleg
    0.63
     AttributeError
    0.63
     Speak
    0.63
     Consid
    0.62
     Tomato
    0.62
    Activations Density 0.000%

    No Known Activations