© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50720
    Prev
    Next
    INDEX
    Explanations

    de followed by names

    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_31_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
    稞
    0.36
    obao
    0.33
     behaviors
    0.33
     studenti
    0.33
     пользователи
    0.33
     (%
    0.32
     sot
    0.32
     eutectic
    0.32
    irical
    0.32
     रोगी
    0.32
    POSITIVE LOGITS
    nextLine
    0.41
     другого
    0.35
    再去
    0.34
    媟
    0.34
     আশ্রয়
    0.34
     እድ
    0.33
     Identification
    0.33
    กรา
    0.33
    水泥
    0.32
    自然
    0.32
    Activations Density 0.000%

    No Known Activations