© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9137
    Prev
    Next
    INDEX
    Explanations

    County names

    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
    Negative Logits
    𝗮
    3.12
    𝗲
    2.81
    𝗻
    2.60
    ை
    2.59
    岖
    2.57
     Voor
    2.51
    ي
    2.49
     \*
    2.46
    大規模
    2.41
    一流
    2.39
    POSITIVE LOGITS
    <tr>
    2.44
    matic
    2.37
    िंग
    2.33
    ితే
    2.33
    욱
    2.28
    ியான
    2.27
    pictureBox
    2.20
    AutoScaleMode
    2.17
    six
    2.13
    shire
    2.12
    Activations Density 0.001%

    No Known Activations