© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81110
    Prev
    Next
    INDEX
    Explanations

    secret

    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
    emper
    0.41
    zhu
    0.38
     Zut
    0.38
     ذر
    0.37
    zta
    0.35
     بإ
    0.35
     zhu
    0.35
    振
    0.35
     Allentown
    0.34
     DU
    0.34
    POSITIVE LOGITS
     সমু
    0.42
    enames
    0.41
    ocurrencies
    0.40
    ésus
    0.38
    TorpedoStore
    0.37
     Bayes
    0.37
    ্রয়
    0.37
    🍌
    0.37
     स्के
    0.36
     equalities
    0.36
    Activations Density 0.001%

    No Known Activations