© 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. 38153
    Prev
    Next
    INDEX
    Explanations

    hope and related words

    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
    ၷ
    0.66
     اکاؤن
    0.65
    ਰ
    0.65
    ר
    0.64
    Ⴚ
    0.64
    на
    0.63
     امریکہ
    0.63
     انڈیا
    0.62
    शेखर
    0.61
     WindowStateType
    0.61
    POSITIVE LOGITS
    0.85
    s
    0.70
    Ad
    0.65
    IL
    0.64
    ante
    0.63
    _
    0.62
    il
    0.61
    ud
    0.60
     was
    0.59
    II
    0.59
    Activations Density 0.001%

    No Known Activations