© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14319
    Prev
    Next
    INDEX
    Explanations

    initiated or originated

    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
    χ
    0.48
    위
    0.46
    اف
    0.46
    함으로써
    0.44
    TLV
    0.44
    CR
    0.43
    ARB
    0.43
    স্বাস্থ্য
    0.43
    轟
    0.43
    共に
    0.43
    POSITIVE LOGITS
     отно
    0.52
     ສ
    0.50
     complacent
    0.49
     contented
    0.48
     vac
    0.48
    适应
    0.47
     central
    0.46
    ículos
    0.46
     impres
    0.46
     pretensions
    0.45
    Activations Density 0.000%

    No Known Activations