© 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. 8893
    Prev
    Next
    INDEX
    Explanations

    Scarleteen

    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
    ので
    2.02
     moe
    1.79
    för
    1.72
    ه
    1.69
     contemplated
    1.69
    o
    1.68
    bash
    1.67
    त
    1.64
     müs
    1.63
    ह
    1.58
    POSITIVE LOGITS
    cknowled
    1.73
    ﺶ
    1.72
     undulating
    1.69
    denly
    1.69
    SM
    1.64
    可以看出
    1.60
    \(
    1.57
    اا
    1.55
    نش
    1.55
    yyyyyyyy
    1.55
    Activations Density 0.001%

    No Known Activations