© 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. 35528
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     bén
    0.43
     갑
    0.41
     Hooker
    0.39
     фон
    0.38
    quen
    0.37
     کہیں
    0.37
    たり
    0.37
     בן
    0.36
     gab
    0.36
     माला
    0.36
    POSITIVE LOGITS
     porridge
    0.38
     মির
    0.37
    omorf
    0.37
    вари
    0.37
    楲
    0.36
    nett
    0.36
    wString
    0.36
     varieg
    0.36
    heiro
    0.36
    ニャ
    0.36
    Activations Density 0.000%

    No Known Activations