© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217301
    Prev
    Next
    INDEX
    Explanations

    academic citations and references

    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_31_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
    ubicin
    0.35
     опреде
    0.34
     Pré
    0.34
     "-",
    0.34
     accomplishment
    0.34
     সিরিজে
    0.34
    镯
    0.34
     ประก
    0.33
     effort
    0.33
     behaupt
    0.33
    POSITIVE LOGITS
     yaad
    0.39
     قان
    0.38
    扫
    0.38
     அற
    0.38
    Contain
    0.38
     পড়ার
    0.37
    𝗧
    0.37
    Projectile
    0.37
    ỉnh
    0.37
    history
    0.37
    Activations Density 0.001%

    No Known Activations