© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230474
    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_6_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
    is
    1.49
    ي
    1.34
    i
    1.20
    ك
    1.13
    ма
    1.10
    an
    1.06
    aton
    1.04
    c
    1.04
    ти
    1.02
    n
    1.02
    POSITIVE LOGITS
     Fundación
    0.92
     bandage
    0.90
     ALL
    0.88
     Și
    0.88
    BILL
    0.87
     ship
    0.85
     hasilnya
    0.85
     Fundação
    0.85
    น้ำ
    0.84
     view
    0.82
    Activations Density 0.000%

    No Known Activations