© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205109
    Prev
    Next
    INDEX
    Explanations

    Ankara, turkish, union, connection, ease

    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_37_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
    usse
    0.38
     लय
    0.38
    Coupon
    0.38
     caméra
    0.37
    ょ
    0.37
    Public
    0.37
     громад
    0.37
     accretion
    0.37
     tenant
    0.36
    Guid
    0.36
    POSITIVE LOGITS
     피해
    0.36
     turkish
    0.36
    zov
    0.36
     Boz
    0.35
     Ekonomi
    0.35
     Ankara
    0.34
     칸
    0.34
     ഫാ
    0.34
     AKP
    0.34
    IDField
    0.34
    Activations Density 0.000%

    No Known Activations