© 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. 144612
    Prev
    Next
    INDEX
    Explanations

    hidalgo / a base

    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
     is
    2.08
    ك
    1.98
    ية
    1.85
    ير
    1.72
    يس
    1.51
    వ
    1.41
    কে
    1.38
    را
    1.34
    ש
    1.33
    لا
    1.31
    POSITIVE LOGITS
    il
    2.08
    et
    1.92
    um
    1.70
    ar
    1.67
    ak
    1.66
    ur
    1.60
    i
    1.59
    er
    1.52
    :
    1.50
    for
    1.45
    Activations Density 0.000%

    No Known Activations