© 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. 13808
    Prev
    Next
    INDEX
    Explanations

    processes and documentation

    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
    adə
    0.44
     घड़ी
    0.43
     Bree
    0.41
    Blockchain
    0.40
     चाइ
    0.38
    DataMat
    0.38
    榈
    0.38
    PLIED
    0.38
     Blockchain
    0.37
     शिवम
    0.37
    POSITIVE LOGITS
    Von
    0.44
    ට්ට
    0.42
     насыщен
    0.39
    eva
    0.37
    碾
    0.36
    Asp
    0.36
    羨
    0.36
     propos
    0.35
    gers
    0.35
     রামগতি
    0.35
    Activations Density 0.002%

    No Known Activations