© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203112
    Prev
    Next
    INDEX
    Explanations

    localStorage.getItem

    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_25_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
     それぞれ
    0.41
    }.}
    0.37
     ແມ່ນ
    0.37
    dsp
    0.37
    طقة
    0.35
    styling
    0.35
    ബോ
    0.35
    線を
    0.35
    ଅ
    0.35
    Kar
    0.35
    POSITIVE LOGITS
     cocaine
    0.39
     testosterone
    0.39
     checks
    0.39
     Checks
    0.38
    收
    0.38
     coke
    0.38
     checked
    0.37
     (
    0.36
     COC
    0.36
     Method
    0.35
    Activations Density 0.000%

    No Known Activations