© 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. 7873
    Prev
    Next
    INDEX
    Explanations

    dependency group IDs

    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
    י
    2.67
    ০
    2.48
    ν
    2.20
    ি
    2.13
    и
    2.04
    ي
    2.01
     grips
    1.96
    कर्ता
    1.93
     dozen
    1.92
    ు
    1.91
    POSITIVE LOGITS
    م
    2.06
    likes
    2.05
     изучения
    1.99
     attuned
    1.97
     Durchführung
    1.96
     excreted
    1.96
    വ്
    1.86
    ના
    1.83
     fortement
    1.76
     congratulate
    1.76
    Activations Density 0.001%

    No Known Activations