© 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. 179572
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    بو
    0.41
    사이트
    0.39
    𝐵
    0.39
     über
    0.39
     P
    0.38
    бо
    0.38
     aggreg
    0.38
     decks
    0.38
    σί
    0.38
     booms
    0.38
    POSITIVE LOGITS
    ими
    0.41
    тами
    0.39
    iega
    0.36
     Craven
    0.36
    разде
    0.36
    hutang
    0.35
    xt
    0.35
     습
    0.35
     cen
    0.35
     अंग
    0.35
    Activations Density 0.000%

    No Known Activations