© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82670
    Prev
    Next
    INDEX
    Explanations

    addresses and locations

    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_53_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
    瑷
    0.44
     Bunda
    0.43
    枞
    0.43
     वस्तू
    0.41
     अभिव
    0.40
    Authent
    0.40
    তনা
    0.39
     Vertex
    0.39
    Տ
    0.38
     Ти
    0.38
    POSITIVE LOGITS
     Nick
    0.42
     scler
    0.41
    Nick
    0.40
     Caputo
    0.40
     cuc
    0.39
    geojson
    0.39
     rob
    0.38
    Fitz
    0.38
     encapsulated
    0.38
    カロ
    0.38
    Activations Density 0.002%

    No Known Activations