© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1000
    Prev
    Next
    INDEX
    Explanations

    thank you closings

    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_39_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
    LONDON
    0.41
    ⊡
    0.40
    იღ
    0.40
    Gert
    0.37
     উদ্বাস্ত
    0.37
    Tray
    0.37
    жуть
    0.37
    Singolare
    0.36
    Hurricane
    0.36
    츄
    0.35
    POSITIVE LOGITS
     Correct
    0.48
     Shouldn
    0.46
     name
    0.43
     Below
    0.43
     Could
    0.42
     Runs
    0.42
     below
    0.42
     Example
    0.41
     Name
    0.41
     runs
    0.41
    Activations Density 0.106%

    No Known Activations