© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78050
    Prev
    Next
    INDEX
    Explanations

    Joseph

    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_53_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
    relsen
    0.43
     thicken
    0.40
    炡
    0.40
     Erick
    0.38
    ™
    0.38
     thickening
    0.37
    ону
    0.36
     Ер
    0.36
    嘎
    0.36
     Periods
    0.36
    POSITIVE LOGITS
    ُ
    0.45
    Joseph
    0.40
     Joseph
    0.39
    Custom
    0.38
     joseph
    0.38
    U
    0.37
     JOSEPH
    0.37
    alco
    0.37
    ॅप
    0.36
    hormat
    0.36
    Activations Density 0.009%

    No Known Activations