© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18865
    Prev
    Next
    INDEX
    Explanations

    scripting and scriptable objects

    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_40_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
     休
    0.45
     siting
    0.42
    㖷
    0.40
     डिप्लो
    0.40
    🍴
    0.40
    ⌔
    0.39
    户外
    0.39
     휴
    0.38
    Cond
    0.38
    ВИ
    0.37
    POSITIVE LOGITS
    ovaných
    0.38
     بسيطه
    0.38
     વિકાસ
    0.38
    Development
    0.37
     Development
    0.37
     nerv
    0.36
     розви
    0.36
     добро
    0.36
     pinn
    0.36
     розвитку
    0.35
    Activations Density 0.003%

    No Known Activations