© 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. 208412
    Prev
    Next
    INDEX
    Explanations

    list methods

    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
    리고
    0.38
     संभालने
    0.38
     وإ
    0.37
    婚礼
    0.35
     Dost
    0.34
    )':
    0.34
    binder
    0.34
     ['
    0.34
     wedding
    0.34
    ressor
    0.34
    POSITIVE LOGITS
    ளாக்
    0.40
    Sliders
    0.37
    ittura
    0.36
     intrusions
    0.35
     desktops
    0.35
     godina
    0.34
    Area
    0.34
    azeera
    0.34
    আরো
    0.34
    櫥
    0.34
    Activations Density 0.001%

    No Known Activations