© 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. 230914
    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
    inį
    1.08
    inę
    1.01
    është
    1.00
    agamanam
    0.95
    ᱾
    0.95
     οποίο
    0.93
    entityManager
    0.91
    in
    0.90
     Russische
    0.90
    )।
    0.89
    POSITIVE LOGITS
    '
    1.71
    on
    1.31
    un
    1.23
    ’
    1.21
    ت
    1.20
    τ
    1.05
    ن
    0.99
    ro
    0.97
    is
    0.96
    ig
    0.94
    Activations Density 0.000%

    No Known Activations