© 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. 215656
    Prev
    Next
    INDEX
    Explanations

    PCA

    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
    mé
    0.41
    ớ
    0.41
    ache
    0.40
    ání
    0.39
    či
    0.39
    álise
    0.39
    M
    0.39
    NCc
    0.38
    zás
    0.38
    ME
    0.38
    POSITIVE LOGITS
     handing
    0.42
    懷
    0.38
     Marathon
    0.38
     Jakob
    0.38
     মুর
    0.38
     қў
    0.37
    원으로
    0.37
     ана
    0.37
     prestataire
    0.36
     मिळ
    0.36
    Activations Density 0.000%

    No Known Activations