© 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. 52888
    Prev
    Next
    INDEX
    Explanations

    faith and love

    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
    绿
    0.43
     childhood
    0.40
    があれば
    0.39
     Inferno
    0.38
     boyhood
    0.37
    🔙
    0.36
     youthful
    0.35
     entrance
    0.35
     Childhood
    0.35
     đu
    0.35
    POSITIVE LOGITS
    鹽
    0.39
    aita
    0.38
    Exper
    0.37
    approche
    0.37
     vorge
    0.37
    SelectSingle
    0.36
    itipi
    0.36
     universo
    0.36
    ОВО
    0.35
    Lamb
    0.35
    Activations Density 0.014%

    No Known Activations