© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 87078
    Prev
    Next
    INDEX
    Explanations

    languages and suffixes

    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_18_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
     L
    0.52
     casualty
    0.50
     casualties
    0.49
     Pro
    0.49
     P
    0.48
     For
    0.47
    d
    0.46
    a
    0.46
     c
    0.45
     motion
    0.45
    POSITIVE LOGITS
     Gericht
    0.53
    τητα
    0.52
    性别
    0.52
     Wikiseite
    0.51
     여러분
    0.50
     জনগণ
    0.50
    ính
    0.50
    ését
    0.50
     နှစ်
    0.49
     తన
    0.48
    Activations Density 0.000%

    No Known Activations