© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16889
    Prev
    Next
    INDEX
    Explanations

    past presidents and appointments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     vyst
    0.38
     Strengthen
    0.37
     vess
    0.37
     unterstüt
    0.36
    perman
    0.36
    ากร
    0.34
     isDisabled
    0.34
    声
    0.34
     streng
    0.33
    Colon
    0.33
    POSITIVE LOGITS
    сом
    0.40
     appointments
    0.39
     appointing
    0.39
    zie
    0.38
     UP
    0.38
    appointments
    0.38
     Eddie
    0.37
     ഒഴ
    0.37
    éditeur
    0.37
     అయ
    0.36
    Activations Density 0.001%

    No Known Activations