© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197106
    Prev
    Next
    INDEX
    Explanations

    l

    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
     ERIC
    0.43
     Eric
    0.42
    Eric
    0.41
     BEA
    0.41
     CH
    0.40
    কিন
    0.38
    ERIC
    0.38
     జ
    0.38
     eric
    0.38
     Manila
    0.38
    POSITIVE LOGITS
    V
    0.39
    铄
    0.38
     واخ
    0.38
    Ns
    0.37
    Segue
    0.37
    usser
    0.37
    ঙ্ঘ
    0.36
    ibor
    0.36
    footnotes
    0.36
    ológ
    0.36
    Activations Density 0.002%

    No Known Activations