© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51013
    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_30_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
     було
    0.42
    ENCI
    0.42
     दाखिल
    0.37
     mengen
    0.37
     Эль
    0.37
     mieszkań
    0.36
    }}}
    0.36
    constit
    0.35
     সব্ব
    0.35
    }}}=\
    0.35
    POSITIVE LOGITS
     motivational
    0.40
     dụng
    0.40
     rebranded
    0.39
     dend
    0.38
    概率
    0.38
     motivation
    0.37
     بالس
    0.37
    它们
    0.37
     watering
    0.36
    motivation
    0.36
    Activations Density 0.000%

    No Known Activations