© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235444
    Prev
    Next
    INDEX
    Explanations

    Esperanto, code

    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_46_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
    йд
    0.40
    സ്റ്റി
    0.39
    iky
    0.38
     ஹா
    0.38
    itiert
    0.38
    ikke
    0.37
     होश
    0.36
    ﻅ
    0.36
    hbs
    0.36
    বাদ
    0.36
    POSITIVE LOGITS
     call
    0.46
     Call
    0.42
     species
    0.41
    Call
    0.41
    ㄢ
    0.40
     AC
    0.38
     AN
    0.38
     especific
    0.38
     theorem
    0.37
     js
    0.37
    Activations Density 0.009%

    No Known Activations