© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207497
    Prev
    Next
    INDEX
    Explanations

    hereby

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    thane
    0.38
    Bean
    0.37
    岗
    0.36
    ক্টো
    0.35
    ార
    0.34
     Refs
    0.34
     Treated
    0.34
     Bamboo
    0.34
    Bamboo
    0.34
    ᱩ
    0.34
    POSITIVE LOGITS
     hereby
    1.45
    在此
    1.02
    特
    0.97
     herewith
    0.94
     HERE
    0.86
    here
    0.79
     whereby
    0.77
     Thereby
    0.76
    HERE
    0.75
     her
    0.73
    Activations Density 0.002%

    No Known Activations