© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13345
    Prev
    Next
    INDEX
    Explanations

    phone models

    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_13_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
    Im
    0.46
    Hemos
    0.44
    Muchas
    0.43
     claw
    0.43
    Kan
    0.41
    Ļ
    0.41
    etku
    0.40
    JAR
    0.40
    tier
    0.39
    Tier
    0.39
    POSITIVE LOGITS
     க
    0.49
     multiplets
    0.48
     ally
    0.46
     prodotto
    0.46
     regressions
    0.46
    MainActivityTest
    0.43
     защита
    0.43
    galaxys
    0.43
    rectionType
    0.43
    ropathy
    0.42
    Activations Density 0.003%

    No Known Activations