© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195696
    Prev
    Next
    INDEX
    Explanations

    Fore

    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
    mers
    0.40
    гран
    0.39
    ivasena
    0.39
     الارد
    0.38
    NESS
    0.37
     Coles
    0.37
    کاروں
    0.36
    壢
    0.36
    湄
    0.36
     Mois
    0.36
    POSITIVE LOGITS
    kinase
    0.46
    ophores
    0.43
    kte
    0.41
    pse
    0.39
    Cow
    0.39
    otive
    0.39
    aceutical
    0.39
    ece
    0.38
    forge
    0.38
    clidean
    0.38
    Activations Density 0.001%

    No Known Activations