© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75285
    Prev
    Next
    INDEX
    Explanations

    answer key

    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_31_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
    Pane
    0.37
     inscripción
    0.37
    하면
    0.36
    邦
    0.36
    Hob
    0.36
     Defining
    0.35
     Jude
    0.35
    Ev
    0.35
     Yun
    0.35
     Championship
    0.34
    POSITIVE LOGITS
     patent
    0.40
     veterinary
    0.39
     (%
    0.35
    [%
    0.35
     なお
    0.35
    emploi
    0.35
     tốt
    0.34
    ឆ្ល
    0.34
     prow
    0.34
    dipl
    0.34
    Activations Density 0.003%

    No Known Activations