© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199361
    Prev
    Next
    INDEX
    Explanations

    elements: Earth, Water, Fire

    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_12_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
     jednu
    0.57
    ਐ
    0.55
     apareció
    0.53
    एस
    0.52
     schwarzen
    0.52
    स्ताना
    0.52
    എസ്
    0.51
     Sudden
    0.50
     Spots
    0.50
    ğa
    0.49
    POSITIVE LOGITS
    ن
    0.52
    Deleg
    0.50
    n
    0.49
    ther
    0.48
    Artifact
    0.47
    бли
    0.46
    ରି
    0.46
    Triangle
    0.46
     transceiver
    0.46
    Thailand
    0.44
    Activations Density 0.000%

    No Known Activations