© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242014
    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_40_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
    SMP
    0.39
     TAT
    0.38
    込む
    0.38
    ∋
    0.37
    россий
    0.37
    building
    0.37
    孛
    0.36
    NGO
    0.36
     পরিষদে
    0.36
     DBox
    0.36
    POSITIVE LOGITS
     fascinated
    0.38
    ogène
    0.37
     கவர்
    0.36
     অন্ধ
    0.35
     svc
    0.35
     caz
    0.34
     Opinions
    0.34
    饭
    0.34
    इनस
    0.34
     admire
    0.34
    Activations Density 0.000%

    No Known Activations