© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213001
    Prev
    Next
    INDEX
    Explanations

    Adam's apple

    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_5_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
    of
    1.68
    ig
    1.50
    ما
    1.44
    v
    1.43
    بر
    1.37
    ش
    1.37
    og
    1.28
    ض
    1.28
    ט
    1.28
    д
    1.27
    POSITIVE LOGITS
    ו
    1.51
    ो
    1.20
     I
    1.10
    ू
    1.10
     .)
    1.09
     Перейти
    1.02
     It
    0.98
     papá
    0.96
    PORT
    0.95
    IEN
    0.95
    Activations Density 0.000%

    No Known Activations