© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121788
    Prev
    Next
    INDEX
    Explanations

    context prompts questions

    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_27_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
    計算
    0.37
    chosen
    0.35
     আবার
    0.35
    硋
    0.35
     janela
    0.35
    textview
    0.35
     അവസ
    0.34
    acute
    0.34
    кә
    0.34
     escolher
    0.34
    POSITIVE LOGITS
     sarcom
    0.39
    SUP
    0.38
    ባቢ
    0.37
     하면
    0.36
    뇌
    0.36
    Conflict
    0.35
     frau
    0.35
     भवन
    0.35
    ynyt
    0.35
    ዪ
    0.35
    Activations Density 0.091%

    No Known Activations