© 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. 11860
    Prev
    Next
    INDEX
    Explanations

    over / across / spread

    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
    𝚟
    0.62
    rified
    0.61
    ant
    0.60
    ffle
    0.59
    р
    0.57
     ϒ
    0.57
    pple
    0.55
     ஆனால்
    0.55
    ration
    0.54
    ون
    0.54
    POSITIVE LOGITS
    \
    0.79
    写
    0.55
     shi
    0.54
     Consent
    0.54
     Cre
    0.53
     बैड
    0.52
     Func
    0.52
     Michelin
    0.52
     Matt
    0.51
     Prest
    0.51
    Activations Density 0.038%

    No Known Activations