© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150934
    Prev
    Next
    INDEX
    Explanations

    level or class followed by a noun

    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_23_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
     आणि
    0.42
     şi
    0.36
     và
    0.36
    และ
    0.35
     還
    0.35
    竑
    0.35
     wɔ
    0.34
    ariance
    0.34
     আৰু
    0.34
    ；
    0.33
    POSITIVE LOGITS
    pdbonly
    0.32
     others
    0.32
     fl
    0.31
     burn
    0.31
     sucker
    0.30
    ចំ
    0.29
     versions
    0.29
     Stray
    0.29
     gradual
    0.29
     tr
    0.28
    Activations Density 0.005%

    No Known Activations