© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9462
    Prev
    Next
    INDEX
    Explanations

    both

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     mấy
    0.80
    与其他
    0.77
    마다
    0.75
    ರ್
    0.70
     hanem
    0.68
    들이
    0.68
     "=",
    0.67
    ṯ
    0.66
    মের
    0.66
    所在的
    0.65
    POSITIVE LOGITS
     both
    5.76
    both
    5.29
     Both
    5.15
    Both
    5.15
     BOTH
    4.56
     दोनों
    4.16
     både
    4.14
     entrambi
    4.01
     ambos
    3.99
    दोनों
    3.95
    Activations Density 0.818%

    No Known Activations