© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 216451
    Prev
    Next
    INDEX
    Explanations

    root

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     BEE
    0.59
    Bee
    0.53
     Bee
    0.52
     bee
    0.50
    닭
    0.44
     Chicken
    0.44
     chicken
    0.42
    UpperCase
    0.42
    ጫ
    0.41
    chicken
    0.41
    POSITIVE LOGITS
     Wurzel
    0.41
    根
    0.41
     корне
    0.41
    Bur
    0.40
     G
    0.40
     Barg
    0.40
     Bur
    0.38
     Bak
    0.38
    ន្
    0.38
    സ്ത
    0.38
    Activations Density 0.057%

    No Known Activations