© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236801
    Prev
    Next
    INDEX
    Explanations

    contractual parties and roles

    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_32_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
     Led
    0.38
     জোর
    0.37
    Permission
    0.36
    patial
    0.34
    possible
    0.33
     possible
    0.33
     Malibu
    0.33
     ឬ
    0.33
    uala
    0.33
    KURZ
    0.33
    POSITIVE LOGITS
    IEE
    0.43
     finisher
    0.42
    IMA
    0.38
     PSW
    0.37
    ima
    0.36
     finishers
    0.36
     Euse
    0.35
     Conform
    0.34
    outi
    0.34
    🤝
    0.34
    Activations Density 0.001%

    No Known Activations