© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 51369
    Prev
    Next
    INDEX
    Explanations

    subtract X from both sides

    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
     alcanzó
    0.38
    收到
    0.38
    邡
    0.38
    是通过
    0.38
    にい
    0.37
     হাও
    0.37
    ამდე
    0.37
     صاف
    0.37
    +}(
    0.36
    ahi
    0.36
    POSITIVE LOGITS
    Paul
    0.40
    Mol
    0.37
     mol
    0.36
     Rap
    0.36
     Paul
    0.36
    RAP
    0.36
     spal
    0.36
     Mol
    0.36
     rap
    0.36
     Calcul
    0.35
    Activations Density 0.027%

    No Known Activations