© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63268
    Prev
    Next
    INDEX
    Explanations

    names

    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_59_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
     gere
    0.53
    PA
    0.42
    anooga
    0.41
     ϕ
    0.39
    בו
    0.39
    ಪಾ
    0.38
    TA
    0.37
    मिताभ
    0.37
     কলিক
    0.37
    猾
    0.37
    POSITIVE LOGITS
     AUR
    0.71
     Darren
    0.66
    Aur
    0.66
     Aur
    0.65
     Garrett
    0.65
     Aro
    0.65
    aur
    0.65
     करीना
    0.65
    AUR
    0.65
     aur
    0.64
    Activations Density 0.004%

    No Known Activations