© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 215262
    Prev
    Next
    INDEX
    Explanations

    young

    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
     rhod
    0.40
    ParentObject
    0.39
    蛍光
    0.38
    蓉
    0.37
    dout
    0.36
     Rhod
    0.36
    inflate
    0.36
     condomin
    0.36
    shade
    0.35
    頌
    0.35
    POSITIVE LOGITS
     giovane
    0.51
     young
    0.49
     YOUNG
    0.48
     युवा
    0.48
     jeunes
    0.48
    年輕
    0.47
     Young
    0.46
    Young
    0.46
     jovem
    0.44
    埔
    0.44
    Activations Density 0.001%

    No Known Activations