© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60948
    Prev
    Next
    INDEX
    Explanations

    builtin.com

    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
    σε
    0.46
    isering
    0.45
     entiende
    0.42
    يل
    0.41
    iscono
    0.41
    லைக்
    0.41
    ә
    0.40
    鼗
    0.40
    ப்த
    0.39
    ној
    0.39
    POSITIVE LOGITS
     pouvoir
    0.40
     HIV
    0.37
    <0xE3>
    0.36
     Bollywood
    0.36
     analyzers
    0.35
     McGraw
    0.35
     stays
    0.34
     Muller
    0.34
     masculinity
    0.34
     Sahara
    0.34
    Activations Density 0.001%

    No Known Activations