© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 147713
    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_18_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
    低温
    0.48
    kü
    0.48
    exhaustive
    0.45
    k
    0.45
     is
    0.44
    kir
    0.44
    nur
    0.44
     использова
    0.43
    </h1>
    0.42
    кро
    0.42
    POSITIVE LOGITS
     αδ
    0.51
    🍐
    0.51
     ဂ
    0.50
     αρ
    0.49
    的学习
    0.48
     अर
    0.47
     Leibnitz
    0.47
     个
    0.46
    𒐤
    0.46
    వంటి
    0.46
    Activations Density 0.000%

    No Known Activations