© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195971
    Prev
    Next
    INDEX
    Explanations

    where possible

    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_4_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
    0.70
     on
    0.70
    ला
    0.69
    ல்
    0.65
     svou
    0.62
    的
    0.62
    كي
    0.61
    on
    0.59
     has
    0.59
    ла
    0.58
    POSITIVE LOGITS
     руху
    0.59
     согласо
    0.57
    ݨ
    0.55
     питань
    0.54
    ġ
    0.52
    ног
    0.51
    förm
    0.50
    irt
    0.49
    ні
    0.48
     संसाधनों
    0.48
    Activations Density 0.002%

    No Known Activations