© 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. 2888
    Prev
    Next
    INDEX
    Explanations

    customer service helpline

    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
    كلات
    0.38
    ρεία
    0.36
    ENTIAL
    0.35
     ಪು
    0.35
    medallas
    0.34
    쭉
    0.33
    arkan
    0.33
    }<\
    0.33
     zipper
    0.33
    отя
    0.33
    POSITIVE LOGITS
     call
    2.88
    call
    2.59
     Call
    2.55
    Call
    2.53
     CALL
    2.14
    CALL
    2.08
     कॉल
    1.80
    呼
    1.69
     calls
    1.62
     Calls
    1.52
    Activations Density 0.101%

    No Known Activations