© 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. 143233
    Prev
    Next
    INDEX
    Explanations

    environment variables

    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
     punctuated
    0.40
    Tell
    0.40
    deb
    0.39
     automatically
    0.39
     Gere
    0.39
     aligned
    0.39
    J
    0.38
     rele
    0.37
    Sy
    0.37
     punte
    0.36
    POSITIVE LOGITS
     সতর্ক
    0.40
     修改
    0.39
     \%)$
    0.39
     pathogens
    0.38
    ίζουν
    0.38
    काइ
    0.38
    ريبي
    0.38
     রস
    0.37
     webhook
    0.36
     elenco
    0.36
    Activations Density 0.003%

    No Known Activations