© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209049
    Prev
    Next
    INDEX
    Explanations

    for exploring

    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_20_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
    Female
    0.46
    ACP
    0.43
    zy
    0.41
    db
    0.40
     Female
    0.40
    EB
    0.40
    콤
    0.40
    yx
    0.39
    sette
    0.39
    孢
    0.39
    POSITIVE LOGITS
     parar
    0.44
     alarms
    0.42
     secondaires
    0.42
     concealment
    0.41
     jurisdictions
    0.41
     Glas
    0.41
    িয়াছেন
    0.39
     використову
    0.39
     esencial
    0.39
     Estes
    0.39
    Activations Density 0.001%

    No Known Activations