© 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. 12223
    Prev
    Next
    INDEX
    Explanations

    desalination

    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
    τός
    0.57
     footpath
    0.55
    onuclease
    0.52
     球
    0.49
     mapView
    0.49
     града
    0.49
    edos
    0.48
    árm
    0.47
    лива
    0.46
    stateMutability
    0.45
    POSITIVE LOGITS
    B
    0.59
    il
    0.58
    র্জন
    0.53
    most
    0.52
     jato
    0.52
     générateur
    0.52
     cherche
    0.51
     Liberty
    0.50
    یا
    0.50
     apparent
    0.50
    Activations Density 0.003%

    No Known Activations