© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44370
    Prev
    Next
    INDEX
    Explanations

    correctly uses

    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_22_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
    idazol
    0.33
     lineales
    0.32
     پڑھیئے
    0.32
    św
    0.32
    ylül
    0.31
     అందు
    0.30
     lesz
    0.30
    垁
    0.30
    icules
    0.30
     człon
    0.30
    POSITIVE LOGITS
     bel
    0.32
    वाड़ी
    0.32
     bravo
    0.31
     renovating
    0.31
     Champion
    0.30
     Bellev
    0.30
     Zumba
    0.30
     WiFi
    0.30
     shampoo
    0.30
     SPI
    0.29
    Activations Density 0.004%

    No Known Activations