© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213390
    Prev
    Next
    INDEX
    Explanations

    work

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ³
    0.46
     move
    0.41
    adolu
    0.40
     Pro
    0.40
     moving
    0.40
    Steps
    0.38
    孺
    0.38
     li
    0.38
     moved
    0.38
     Baker
    0.38
    POSITIVE LOGITS
     格
    0.40
     Wynne
    0.40
    ग्रहण
    0.39
    วิ
    0.38
     процеду
    0.38
    गणना
    0.36
    מיני
    0.36
     formalities
    0.35
    quine
    0.35
     comunica
    0.35
    Activations Density 0.001%

    No Known Activations