© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88141
    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_23_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
     యువ
    0.54
     hablando
    0.41
     resembles
    0.40
     tasteless
    0.40
     gaming
    0.39
    ኢ
    0.39
     minced
    0.39
     tasted
    0.39
     catalyzed
    0.38
    につなが
    0.38
    POSITIVE LOGITS
    ትክል
    0.46
    洼
    0.44
    łu
    0.44
    Año
    0.43
    ים
    0.42
     कोषा
    0.42
    кола
    0.41
    쐞
    0.41
     commission
    0.41
    Nw
    0.41
    Activations Density 0.000%

    No Known Activations