© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8118
    Prev
    Next
    INDEX
    Explanations

    Verde, op, 5

    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
    情况下
    2.95
    ه
    2.89
     translateY
    2.72
    人员
    2.69
    वीं
    2.61
    ย์
    2.57
    ifiably
    2.54
     heatmap
    2.52
    }$-
    2.47
     lalu
    2.45
    POSITIVE LOGITS
    ्स
    2.94
    ━━━━
    2.64
    ς
    2.64
    р
    2.64
    circ
    2.64
    ০
    2.63
    骞
    2.58
    तिहासिक
    2.57
     mund
    2.50
    сона
    2.47
    Activations Density 0.005%

    No Known Activations