© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5295
    Prev
    Next
    INDEX
    Explanations

    code/```

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ভেদ
    0.44
     HEAD
    0.38
     answering
    0.37
     Head
    0.37
    .&
    0.37
     traduction
    0.37
    piej
    0.36
    ꜱ
    0.36
    jeeling
    0.36
     amounting
    0.35
    POSITIVE LOGITS
     BI
    0.42
     কের
    0.40
    BI
    0.39
     Bier
    0.36
    configs
    0.36
    ítico
    0.36
    회를
    0.35
     subserv
    0.35
     Jacobson
    0.35
    ំន
    0.35
    Activations Density 0.050%

    No Known Activations