© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159364
    Prev
    Next
    INDEX
    Explanations

    open up

    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_2_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
    1.06
     (
    0.74
    ।
    0.71
    ᄄ
    0.69
    ،
    0.68
    ".
    0.64
    ৮
    0.63
     Dioc
    0.62
     Zeal
    0.62
     आर
    0.61
    POSITIVE LOGITS
    at
    1.57
    a
    1.46
    ه
    1.39
    ה
    1.30
    is
    1.12
    де
    1.09
    ка
    1.06
    ك
    1.06
    in
    1.05
    ați
    1.02
    Activations Density 0.000%

    No Known Activations