© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31619
    Prev
    Next
    INDEX
    Explanations

    common phrases

    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_50_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
     il
    0.47
     interleukin
    0.39
     mar
    0.39
    ર્ગ
    0.38
    ILT
    0.38
     સી
    0.38
    𝘇
    0.37
    forall
    0.37
    ތ
    0.37
     ding
    0.36
    POSITIVE LOGITS
     hal
    0.46
     Jennie
    0.39
    opu
    0.39
    Roy
    0.39
     hale
    0.39
    hal
    0.38
     hn
    0.37
     Karm
    0.37
     Russo
    0.37
    isement
    0.37
    Activations Density 0.004%

    No Known Activations