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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9246
    Prev
    Next
    INDEX
    Explanations

    web languages

    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
    ヨ
    0.97
     ヨ
    0.83
     y
    0.70
     ys
    0.69
     yǐ
    0.68
     Yud
    0.68
     Yus
    0.66
    vak
    0.66
     பாத
    0.66
    ﾖ
    0.66
    POSITIVE LOGITS
     HTML
    3.66
    HTML
    3.59
     html
    3.58
    html
    3.54
    Html
    3.01
     Html
    2.94
    htm
    2.26
    php
    1.86
     php
    1.80
     PHP
    1.71
    Activations Density 0.189%

    No Known Activations