© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194774
    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_4_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
     funções
    0.55
     партії
    0.51
     ascended
    0.49
     опор
    0.48
     accommodates
    0.48
     matrices
    0.47
     lobbying
    0.47
    刄
    0.47
     regimens
    0.46
     accompagn
    0.46
    POSITIVE LOGITS
    peace
    0.52
    net
    0.50
    ee
    0.48
     Peace
    0.48
     peace
    0.47
    cy
    0.47
    rsquo
    0.46
    kl
    0.46
    </a>
    0.46
    y
    0.45
    Activations Density 0.000%

    No Known Activations