© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204648
    Prev
    Next
    INDEX
    Explanations

    build task definitions

    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_25_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
    鮋
    0.41
    েন্দ্রলাল
    0.41
    겐
    0.38
     ухуд
    0.38
    темати
    0.37
    ｐ
    0.37
    峽
    0.37
    氅
    0.37
    ப்ச
    0.36
     depictions
    0.36
    POSITIVE LOGITS
     TO
    0.45
     Nigel
    0.39
    \/
    0.39
    ique
    0.38
    asse
    0.38
     TDC
    0.37
     tweaked
    0.37
    TO
    0.36
     qui
    0.36
     Siberia
    0.36
    Activations Density 0.000%

    No Known Activations