© 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. 82474
    Prev
    Next
    INDEX
    Explanations

    Italy / Italian

    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
     Compart
    0.72
     compart
    0.69
    Compart
    0.63
    compart
    0.61
     compartment
    0.59
     compartments
    0.55
     sotto
    0.47
    踊
    0.44
     comparte
    0.42
     juntos
    0.41
    POSITIVE LOGITS
     маги
    0.43
    Mu
    0.41
     Му
    0.40
    穆
    0.38
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.38
     Tru
    0.38
     ale
    0.38
     gu
    0.38
     wesentlich
    0.37
    assian
    0.37
    Activations Density 0.003%

    No Known Activations