© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31344
    Prev
    Next
    INDEX
    Explanations

    luxury brands

    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
     K
    0.41
    abar
    0.41
    sq
    0.39
    entric
    0.39
     Continental
    0.37
     Gres
    0.37
     Oceania
    0.37
     Sess
    0.37
    issage
    0.37
    ляти
    0.36
    POSITIVE LOGITS
     W
    0.55
     डब्ल्यू
    0.47
     AIA
    0.46
     womb
    0.46
    Ae
    0.46
    aira
    0.45
    W
    0.43
    ᅢ
    0.43
     Aram
    0.43
    Aes
    0.42
    Activations Density 0.035%

    No Known Activations