© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35764
    Prev
    Next
    INDEX
    Explanations

    Macondo, Macula

    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_3_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
    '
    0.93
    et
    0.82
    at
    0.79
    it
    0.77
    ord
    0.76
    ah
    0.75
    are
    0.75
    بوع
    0.74
    ка
    0.72
    ag
    0.72
    POSITIVE LOGITS
    İN
    0.71
     storm
    0.68
     лиш
    0.66
     elicit
    0.61
     distância
    0.61
     earthquake
    0.59
     wildest
    0.59
    ด
    0.59
    tted
    0.59
     répon
    0.59
    Activations Density 0.005%

    No Known Activations