© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52764
    Prev
    Next
    INDEX
    Explanations

    health and diet

    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_55_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
    Chick
    0.43
    感を
    0.41
    LAUNCH
    0.40
    ihanna
    0.39
    otheli
    0.38
    errit
    0.38
    arrera
    0.38
    룡
    0.38
    anei
    0.38
    oprop
    0.37
    POSITIVE LOGITS
     Bagi
    0.48
     bagi
    0.45
     fracciones
    0.41
     প্রচলিত
    0.38
    Dig
    0.38
    ޮ
    0.36
     Observe
    0.36
     TLR
    0.36
     épars
    0.36
    Notice
    0.35
    Activations Density 0.007%

    No Known Activations