© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6871
    Prev
    Next
    INDEX
    Explanations

    .h header guard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    ра
    2.37
    да
    2.09
    er
    2.08
    ামুটি
    1.98
    ات
    1.97
    ل
    1.95
    ان
    1.92
    ва
    1.89
    ة
    1.88
     pept
    1.82
    POSITIVE LOGITS
     withstand
    2.14
    ⎡
    2.09
    𝙨
    1.99
    k
    1.95
    !\!\
    1.90
     asegura
    1.89
     fillets
    1.88
     majesty
    1.87
    pinephrine
    1.87
     adage
    1.86
    Activations Density 0.004%

    No Known Activations