© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3461
    Prev
    Next
    INDEX
    Explanations

    foreign languages, country names

    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_40_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
    ��
    0.17
     si
    0.15
     activation
    0.15
     twists
    0.15
     activations
    0.14
     customer
    0.14
     mobile
    0.14
     sincer
    0.14
     syrup
    0.14
     telemetry
    0.14
    POSITIVE LOGITS
    㜌
    0.20
    騏
    0.19
    გილ
    0.19
     Maver
    0.19
    蛩
    0.19
    centered
    0.18
     Қ
    0.18
    Aile
    0.18
    itev
    0.18
    ၻ
    0.18
    Activations Density 0.001%

    No Known Activations