© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34854
    Prev
    Next
    INDEX
    Explanations

    client

    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
    س
    1.02
    ل
    1.02
    },
    0.96
    ல்
    0.93
    ל
    0.90
    к
    0.89
    al
    0.87
    s
    0.84
    バ
    0.84
    ),
    0.82
    POSITIVE LOGITS
    0.81
    其他
    0.72
    ését
    0.69
     plaatsen
    0.66
     einzigen
    0.66
     gesamte
    0.61
     legais
    0.61
    chen
    0.61
     الاجتماعي
    0.61
    ки
    0.60
    Activations Density 0.012%

    No Known Activations