© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207117
    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_19_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
     disillusioned
    0.50
    𝓉
    0.47
     значення
    0.47
    先
    0.46
    сь
    0.45
    尊重
    0.45
    юд
    0.44
    오는
    0.44
    یداری
    0.43
     brethren
    0.43
    POSITIVE LOGITS
     occult
    0.48
    gers
    0.46
     personnages
    0.46
    arduino
    0.45
    hypoth
    0.44
    ée
    0.44
     enemies
    0.44
    odeon
    0.44
     गलती
    0.44
    मध्ये
    0.44
    Activations Density 0.000%

    No Known Activations