© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206908
    Prev
    Next
    INDEX
    Explanations

    historical events and healthcare

    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_46_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
    biti
    0.40
    ຮັບ
    0.40
    kaw
    0.39
    𝘦
    0.38
     BE
    0.37
    BJ
    0.37
    함
    0.37
    做了
    0.37
     ब्लाइंड
    0.36
     ভিজ
    0.36
    POSITIVE LOGITS
    AsAction
    0.41
     Keb
    0.40
     Tala
    0.37
     Tach
    0.36
     bluff
    0.36
     Kepler
    0.35
     ключ
    0.35
     lagoon
    0.35
     eixo
    0.35
     Otto
    0.35
    Activations Density 0.000%

    No Known Activations