© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44160
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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
    useful
    0.24
    as
    0.23
    exec
    0.23
    left
    0.22
    ↵
    0.22
     nedenle
    0.22
    due
    0.22
    reduce
    0.22
    0.22
     due
    0.21
    POSITIVE LOGITS
    Benzoimidazol
    0.23
    ोजा
    0.23
    اتف
    0.22
     аспек
    0.22
     REACTOR
    0.22
     चाहर
    0.22
    ጨ
    0.22
    ontiti
    0.21
     রিলি
    0.21
     расте
    0.21
    Activations Density 0.018%

    No Known Activations