© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6513
    Prev
    Next
    INDEX
    Explanations

    Auto or Sec followed by symbols

    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
     tubers
    2.27
    amins
    2.25
    त
    2.24
     potuto
    2.09
    वय
    2.09
    तः
    2.08
     neckline
    2.07
    ف
    2.06
     perpet
    2.04
     intestine
    2.01
    POSITIVE LOGITS
     thứ
    2.03
    west
    2.01
    oretically
    1.94
    െ
    1.93
    पंथी
    1.92
     RoHS
    1.80
    橥
    1.80
    tex
    1.77
    ে
    1.77
    $=\
    1.76
    Activations Density 0.000%

    No Known Activations