© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6107
    Prev
    Next
    INDEX
    Explanations

    releases

    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
    ن
    1.15
     disebabkan
    0.98
    //{
    0.90
     rightly
    0.90
    ﻳ
    0.89
    ش
    0.89
    чер
    0.88
    \:
    0.87
    স
    0.87
    ೀಯ
    0.85
    POSITIVE LOGITS
    т
    1.30
    вшейся
    0.92
     gái
    0.88
    hips
    0.86
    ქვენ
    0.86
     awali
    0.83
    pace
    0.83
     chil
    0.83
     rip
    0.81
    limit
    0.81
    Activations Density 0.000%

    No Known Activations