© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 122338
    Prev
    Next
    INDEX
    Explanations

    `pkg install`

    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_38_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
     பறி
    0.37
    rolyte
    0.37
     coupe
    0.36
    駐
    0.36
    amless
    0.36
     Crouch
    0.35
    ppel
    0.35
     edt
    0.35
    inky
    0.35
    args
    0.35
    POSITIVE LOGITS
     Taro
    0.38
     Aper
    0.38
    解答
    0.38
     Zur
    0.36
     Siemens
    0.36
    ‹
    0.36
     πί
    0.35
    риф
    0.34
     womb
    0.34
    Siem
    0.34
    Activations Density 0.000%

    No Known Activations