© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125058
    Prev
    Next
    INDEX
    Explanations

    work for

    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
    2
    0.99
    us
    0.98
    ة
    0.88
    ing
    0.79
    ed
    0.77
    ↵↵
    0.75
    ek
    0.72
    ok
    0.69
    ہ
    0.66
    ist
    0.64
    POSITIVE LOGITS
    ﻟ
    0.78
     ATMs
    0.67
    ༞
    0.62
    𝖆
    0.61
    ativas
    0.60
    ʚ
    0.59
     awhile
    0.59
     pools
    0.58
     Новосибир
    0.58
    DEPENDENCIA
    0.57
    Activations Density 0.000%

    No Known Activations