© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2088
    Prev
    Next
    INDEX
    Explanations

    immortal realm cultivation divine body

    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_39_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
     Acho
    0.36
     tariffs
    0.36
    ҽ
    0.35
     indoor
    0.35
    ച്ചു
    0.34
    спект
    0.33
    сным
    0.33
    🤔
    0.32
    ANI
    0.32
    SEC
    0.32
    POSITIVE LOGITS
     Heavenly
    0.50
     Martial
    0.45
     Realm
    0.43
    境界
    0.43
     divine
    0.41
    Heaven
    0.41
     cultivation
    0.41
     মের
    0.40
    上品
    0.40
     Dao
    0.39
    Activations Density 0.018%

    No Known Activations