© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14513
    Prev
    Next
    INDEX
    Explanations

    technical processes and operations

    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_34_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
     befinden
    0.41
     знаходиться
    0.39
     znajduje
    0.38
     befindet
    0.38
    が存在
    0.36
     stave
    0.36
    зме
    0.35
    ñ
    0.35
     changed
    0.35
    那里
    0.35
    POSITIVE LOGITS
    しやすい
    0.39
    難しい
    0.38
     क्षमता
    0.36
    ᅬ
    0.36
     کردم
    0.36
    athan
    0.36
     către
    0.35
    opath
    0.35
     ਕੀਤੀ
    0.35
    ंद्व
    0.34
    Activations Density 0.229%

    No Known Activations