© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81824
    Prev
    Next
    INDEX
    Explanations

    серийный

    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_0_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
    ди
    1.55
    _
    1.45
     reunião
    1.41
     negativos
    1.38
     azúcar
    1.37
     violência
    1.37
    ુ
    1.34
     navegar
    1.33
     multiplicação
    1.31
     proteína
    1.31
    POSITIVE LOGITS
    R
    2.00
    N
    1.84
    ح
    1.84
    S
    1.77
    ו
    1.76
    D
    1.55
    L
    1.53
    C
    1.48
    خ
    1.45
    ната
    1.41
    Activations Density 0.000%

    No Known Activations