© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58860
    Prev
    Next
    INDEX
    Explanations

    frequency

    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_11_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
    ultat
    0.52
    o
    0.50
     mån
    0.49
    timer
    0.48
    間の
    0.48
    IONI
    0.48
    ênio
    0.47
    oration
    0.46
    oki
    0.46
    orpion
    0.46
    POSITIVE LOGITS
    ع
    0.53
    я
    0.51
    </blockquote>
    0.50
    我和
    0.50
     Baw
    0.48
    </h2>
    0.48
    ва
    0.46
     Enthusi
    0.46
    </i>
    0.45
     Editors
    0.44
    Activations Density 0.040%

    No Known Activations