© 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. 9114
    Prev
    Next
    INDEX
    Explanations

    Privacy concerns

    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
     والإ
    2.56
     možné
    2.55
    n
    2.43
    ра
    2.39
    d
    2.15
    dü
    2.07
    деа
    2.05
    ن
    2.04
     spéciales
    2.04
    diği
    2.03
    POSITIVE LOGITS
    an
    2.59
     तौर
    2.38
    ко
    2.30
     alignItems
    2.25
    ശ്
    2.22
    orifice
    2.22
     sector
    2.21
     unitary
    2.16
     प्रैक्टिस
    2.13
     Tagore
    2.11
    Activations Density 0.052%

    No Known Activations