© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67537
    Prev
    Next
    INDEX
    Explanations

    input handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
    अर्थ
    0.39
    гура
    0.38
     अर्थ
    0.37
     Africans
    0.36
    lectual
    0.34
     ಮಹ
    0.33
    GBuf
    0.33
     सदस्यता
    0.33
    kaart
    0.33
    扒
    0.33
    POSITIVE LOGITS
     input
    2.39
     Input
    2.22
    input
    2.17
    Input
    2.09
     inputs
    2.05
    输入
    2.03
     Inputs
    1.96
     INPUT
    1.90
    入力
    1.83
     입력
    1.80
    Activations Density 0.021%

    No Known Activations