© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168585
    Prev
    Next
    INDEX
    Explanations

    colleagues and peers

    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_34_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
     Psal
    0.38
     Character
    0.35
     character
    0.34
    キャラクター
    0.34
     Charakter
    0.34
     চরিত্রের
    0.34
     CHARACTER
    0.33
     밝
    0.33
    character
    0.33
     karakter
    0.33
    POSITIVE LOGITS
     wett
    0.36
    Setting
    0.35
    Apparently
    0.33
    荿
    0.33
    quels
    0.33
    Greeting
    0.32
     háb
    0.32
     circunfer
    0.32
     apparently
    0.32
     hoods
    0.32
    Activations Density 0.002%

    No Known Activations