© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197773
    Prev
    Next
    INDEX
    Explanations

    ascii characters and encoding

    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_15_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
    อื่นๆ
    0.49
     versiones
    0.46
     черный
    0.46
    Et
    0.45
    もあります
    0.45
    S
    0.45
     Substit
    0.44
     Substitution
    0.44
    кий
    0.44
    F
    0.44
    POSITIVE LOGITS
     paddock
    0.45
     payload
    0.44
     mousse
    0.44
     sette
    0.44
     bandit
    0.44
     custodians
    0.44
     spal
    0.44
    ovan
    0.43
     paysans
    0.43
     gourd
    0.43
    Activations Density 0.000%

    No Known Activations