© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32803
    Prev
    Next
    INDEX
    Explanations

    rigpa, MD, Fodors, thesaurus, bond

    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_7_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
     be
    1.58
     et
    1.20
     of
    1.07
     the
    1.01
     can
    1.01
     will
    1.01
     e
    0.99
     an
    0.93
     are
    0.86
    ก
    0.86
    POSITIVE LOGITS
    i
    1.13
    e
    0.89
    iéndose
    0.88
    ađ
    0.87
    u
    0.83
    iénd
    0.83
    gmzy
    0.81
    Ｍ
    0.80
    ovány
    0.79
     முறையில்
    0.79
    Activations Density 0.000%

    No Known Activations