© 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. 203055
    Prev
    Next
    INDEX
    Explanations

    .

    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
    рім
    0.38
    篙
    0.38
    gameObject
    0.37
    phantom
    0.37
     መቀ
    0.37
     Clinic
    0.36
     സെക്രട്ട
    0.36
    器材
    0.36
    Между
    0.35
    Mys
    0.35
    POSITIVE LOGITS
     western
    0.45
     бук
    0.39
     Stones
    0.38
    섭
    0.38
    zetten
    0.38
     west
    0.37
     Hal
    0.37
     Westinghouse
    0.37
     হিম
    0.37
    toNumber
    0.37
    Activations Density 0.000%

    No Known Activations