© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87594
    Prev
    Next
    INDEX
    Explanations

    physical environments and settings

    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_3_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
    ﺭ
    0.71
     руковод
    0.65
    𝗅
    0.62
    rising
    0.60
    leva
    0.60
     residuos
    0.60
     lindos
    0.59
     eventuali
    0.57
     propri
    0.57
     parametric
    0.57
    POSITIVE LOGITS
    ق
    0.86
    ك
    0.81
    at
    0.74
    ע
    0.73
    ى
    0.72
    स
    0.71
    다
    0.71
    }");
    0.71
    茦
    0.67
    s
    0.67
    Activations Density 0.039%

    No Known Activations