© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79783
    Prev
    Next
    INDEX
    Explanations

    The Batch AI newsletter

    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_31_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
    اخت
    0.42
    最早
    0.40
    akkhand
    0.40
    琕
    0.40
    対応
    0.39
     subarray
    0.39
    簱
    0.39
    決勝
    0.39
    相比
    0.38
     suble
    0.38
    POSITIVE LOGITS
     America
    0.43
     Америки
    0.39
     Amérique
    0.38
     LOVE
    0.37
     Americas
    0.37
    Amérique
    0.37
     inhab
    0.37
     Love
    0.36
    enuation
    0.36
     amour
    0.36
    Activations Density 0.001%

    No Known Activations