© 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. 109772
    Prev
    Next
    INDEX
    Explanations

    recap

    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
    ت
    1.73
    י
    1.69
    т
    1.60
    ە
    1.35
    ם
    1.34
    תה
    1.29
    ва
    1.27
    ри
    1.24
    ം
    1.24
    ні
    1.22
    POSITIVE LOGITS
    ation
    1.51
    ier
    1.25
    ous
    1.23
    als
    1.12
    nå
    1.07
    illion
    1.03
    ined
    1.02
    ulation
    1.02
    ney
    1.01
    alk
    1.00
    Activations Density 0.001%

    No Known Activations