© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50317
    Prev
    Next
    INDEX
    Explanations

    1-800-843-5678

    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_31_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
     blinds
    0.33
     eternal
    0.32
    *%
    0.31
     usual
    0.31
     Casey
    0.31
     Messiah
    0.31
     Res
    0.30
    掸
    0.30
    বিক
    0.30
     god
    0.30
    POSITIVE LOGITS
    ترة
    0.34
     термин
    0.34
     khám
    0.33
    жено
    0.33
     vais
    0.32
    FragmentManager
    0.32
    Já
    0.31
    มีการ
    0.31
    👵
    0.31
     време
    0.31
    Activations Density 0.002%

    No Known Activations