© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220013
    Prev
    Next
    INDEX
    Explanations

    historical events or periods

    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
    écl
    0.44
     Voting
    0.40
    rocities
    0.39
    ism
    0.39
     Inflation
    0.37
    ണ്
    0.37
     facto
    0.37
    颁
    0.37
    igg
    0.36
    ensions
    0.36
    POSITIVE LOGITS
    तै
    0.39
     서
    0.38
     sublim
    0.38
     허
    0.38
     subtle
    0.37
     djel
    0.35
     Subtle
    0.35
    游戏的
    0.35
     $.
    0.34
     thùng
    0.34
    Activations Density 0.006%

    No Known Activations