© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 59361
    Prev
    Next
    INDEX
    Explanations

    acknowledging

    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
     stylesheet
    0.59
     getWorld
    0.58
     turnout
    0.55
    ྵ
    0.55
    কাতা
    0.54
     कक्कड़
    0.54
     sfida
    0.53
     می
    0.51
     eventdata
    0.51
    Ⴀ
    0.51
    POSITIVE LOGITS
    id
    0.81
    1
    0.77
    im
    0.66
    </h3>
    0.64
    oc
    0.63
    0
    0.61
    ans
    0.61
    ل
    0.59
    </h2>
    0.59
    ي
    0.59
    Activations Density 0.002%

    No Known Activations