© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106255
    Prev
    Next
    INDEX
    Explanations

    arc'teryx beta

    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_1_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
    s
    1.11
    щото
    0.94
     അവർ
    0.79
    ς
    0.79
    мой
    0.78
    el
    0.77
     favoring
    0.76
    '
    0.75
    stances
    0.75
     लड़ा
    0.75
    POSITIVE LOGITS
    ED
    1.37
    า
    1.26
    ž
    1.26
    ang
    1.23
    _
    1.23
    يل
    1.22
    ir
    1.19
    ડ
    1.09
    à
    1.09
    .。
    1.06
    Activations Density 0.000%

    No Known Activations