© 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. 4841
    Prev
    Next
    INDEX
    Explanations

    sequence of integers

    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
     phone
    0.37
    PHONE
    0.36
    కోవడం
    0.33
    施
    0.33
    phone
    0.31
    スマートフォン
    0.31
    polynomial
    0.31
     क्‍या
    0.31
     smartphone
    0.30
    Phone
    0.30
    POSITIVE LOGITS
    ᆷ
    0.30
    ادات
    0.30
    煕
    0.29
    INGO
    0.29
    ingo
    0.28
     обращения
    0.28
     trock
    0.28
     salaire
    0.28
     médic
    0.28
    чет
    0.27
    Activations Density 0.002%

    No Known Activations