© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209145
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    ‌,
    0.43
     Earle
    0.42
     aisément
    0.42
    теры
    0.41
    ":[],
    0.41
    DAO
    0.41
    IPS
    0.41
    хі
    0.41
     причин
    0.40
    ULTURAL
    0.40
    POSITIVE LOGITS
     Pelt
    0.41
    Numerical
    0.37
     Impression
    0.37
     Taco
    0.37
     サマータイヤ
    0.36
     exchange
    0.36
    ammlung
    0.36
     superstitious
    0.36
     <<"
    0.35
    camiseta
    0.35
    Activations Density 0.000%

    No Known Activations