© 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. 81374
    Prev
    Next
    INDEX
    Explanations

    dyed with

    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
    م
    1.74
    ني
    1.63
    د
    1.58
    д
    1.54
    ب
    1.47
    يل
    1.46
    كه
    1.44
    й
    1.41
    ב
    1.39
    لات
    1.38
    POSITIVE LOGITS
    _
    1.81
    LE
    1.67
    d
    1.67
    ent
    1.62
    ai
    1.60
    0
    1.57
    RA
    1.53
    V
    1.52
    R
    1.51
     you
    1.50
    Activations Density 0.000%

    No Known Activations