© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131462
    Prev
    Next
    INDEX
    Explanations

    Joe or Boys

    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_50_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
    श्य
    0.43
    াইন
    0.42
    Domain
    0.40
    中共
    0.38
    ष्मान
    0.38
     保
    0.38
     Empower
    0.38
    SY
    0.37
     若
    0.37
    Evening
    0.36
    POSITIVE LOGITS
     Boy
    0.64
     Joe
    0.63
     Joey
    0.61
     boys
    0.60
     joe
    0.60
    Boys
    0.59
     Boys
    0.58
     boy
    0.58
    boy
    0.58
    Boy
    0.57
    Activations Density 0.005%

    No Known Activations