© 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. 49100
    Prev
    Next
    INDEX
    Explanations

    OY followed by AD

    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
    ଖ
    0.10
     Beschreibung
    0.09
     ext
    0.09
     stumps
    0.09
     aire
    0.09
     brief
    0.09
    LING
    0.09
     manifolds
    0.09
     Brief
    0.08
     vanlig
    0.08
    POSITIVE LOGITS
    يلات
    0.10
    لة
    0.10
     kehadiran
    0.10
    [:,
    0.10
    mutation
    0.10
     Decker
    0.10
    both
    0.10
    iculas
    0.10
     convocatoria
    0.10
    诚
    0.10
    Activations Density 0.056%

    No Known Activations