© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44594
    Prev
    Next
    INDEX
    Explanations

    ultimately/eventually followed by a consequence

    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_3_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
    iş
    0.61
    ні
    0.59
     যারা
    0.59
    yı
    0.58
     ingeniería
    0.57
    IST
    0.57
    か
    0.57
     fera
    0.56
     mayoría
    0.54
    ţi
    0.53
    POSITIVE LOGITS
    لب
    0.79
    ل
    0.71
    lgende
    0.68
    خ
    0.67
    p
    0.63
    l
    0.63
    ژ
    0.61
    inflammation
    0.60
    annies
    0.58
    h
    0.57
    Activations Density 0.001%

    No Known Activations