© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11986
    Prev
    Next
    INDEX
    Explanations

    heaven, heavens

    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_13_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
    in
    0.46
    k
    0.45
    ir
    0.44
    n
    0.43
    栥
    0.42
    ﺪ
    0.40
    ור
    0.40
     Karin
    0.39
     lângă
    0.39
     Excellency
    0.38
    POSITIVE LOGITS
     roofs
    0.46
    ্ু
    0.46
     chão
    0.46
     plataforma
    0.45
    平台
    0.44
    newswire
    0.42
     দাম
    0.41
     Rae
    0.39
    기술
    0.39
    ᱒
    0.39
    Activations Density 0.003%

    No Known Activations