© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41488
    Prev
    Next
    INDEX
    Explanations

    chain of conditions

    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_22_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
     הק
    0.14
     الموافق
    0.13
    utils
    0.13
     המש
    0.13
    5
    0.13
    Queue
    0.12
     المق
    0.12
    ρω
    0.12
    druck
    0.12
     but
    0.12
    POSITIVE LOGITS
     }}(
    0.13
    示す
    0.12
     Vysok
    0.12
     bijective
    0.12
     IPF
    0.11
     #####
    0.11
    ⇅
    0.11
    ≙
    0.11
    ্ধে
    0.11
    ానం
    0.11
    Activations Density 0.213%

    No Known Activations