© 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. 9172
    Prev
    Next
    INDEX
    Explanations

    e.g. Baptist Church, Policy Gradients

    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
    ές
    2.43
    д
    2.36
    vitro
    2.31
    bedrooms
    2.22
    Вели
    2.21
     spawned
    2.20
    OHAMA
    2.19
     speculating
    2.18
     amounts
    2.15
    та
    2.15
    POSITIVE LOGITS
     اینکه
    2.51
     lanjut
    2.45
    ם
    2.17
     lỗi
    2.16
    ع
    2.14
    atter
    2.13
    ose
    2.11
    iful
    2.11
    ה
    2.09
    هِ
    2.07
    Activations Density 0.000%

    No Known Activations