© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237148
    Prev
    Next
    INDEX
    Explanations

    prevent SQL injection

    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_46_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
    attan
    0.38
    UserModel
    0.37
    ссии
    0.36
    মিক্যাল
    0.36
     behavioural
    0.36
    ၅
    0.36
    TARGETTING
    0.35
     Heisenberg
    0.35
     พัน
    0.35
    attam
    0.35
    POSITIVE LOGITS
     Kub
    0.42
    櫸
    0.42
     incline
    0.41
     Chrome
    0.41
     kub
    0.40
    Kub
    0.40
     মুখের
    0.38
     mãi
    0.38
     Toolbar
    0.38
    ôme
    0.38
    Activations Density 0.004%

    No Known Activations