© 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. 92379
    Prev
    Next
    INDEX
    Explanations

    account totals and forward movements

    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
    6
    0.62
     +
    0.60
    Override
    0.57
    ha
    0.54
    ፥
    0.54
    ilih
    0.50
     deceler
    0.50
    <0xE2>
    0.50
    å
    0.50
    а
    0.49
    POSITIVE LOGITS
    বারেই
    0.60
     যুগের
    0.59
    ುಂಬ
    0.57
    ेंगू
    0.55
    ין
    0.55
     llamadas
    0.55
    λαν
    0.55
     impuesto
    0.54
    ಾಮ
    0.52
     infamous
    0.52
    Activations Density 0.024%

    No Known Activations