© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10903
    Prev
    Next
    INDEX
    Explanations

    Ichimoku Cloud

    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_40_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
     excavation
    0.41
     rischi
    0.39
     aftermath
    0.39
    చ్చి
    0.38
    🏩
    0.37
    юнча
    0.37
     cottages
    0.36
    ("@
    0.36
     determinations
    0.36
    ้าร
    0.36
    POSITIVE LOGITS
    International
    0.46
    POV
    0.40
     Internation
    0.40
     International
    0.39
     இயக்கு
    0.38
    纭
    0.38
     án
    0.37
     Bain
    0.36
    دو
    0.36
    Bread
    0.36
    Activations Density 0.000%

    No Known Activations