© 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. 144704
    Prev
    Next
    INDEX
    Explanations

    graphic organizer

    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
    ado
    1.32
    ل
    1.32
     anions
    1.23
     by
    1.10
    л
    1.10
     fenders
    1.09
     alat
    1.07
    них
    1.06
     transcripts
    1.05
     angiography
    1.05
    POSITIVE LOGITS
    ia
    1.95
    y
    1.59
    ing
    1.52
    ри
    1.52
    ла
    1.49
    ת
    1.40
    า
    1.38
    ра
    1.37
    am
    1.35
    కు
    1.27
    Activations Density 0.000%

    No Known Activations