© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170974
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
     케
    1.40
     ке
    1.35
    ケ
    1.26
    เค
    1.16
     কে
    1.10
    케
    1.10
     Ке
    1.09
     ケ
    1.05
     ké
    0.93
     κε
    0.93
    POSITIVE LOGITS
    Chemical
    1.10
     chemical
    1.09
     Chemical
    1.09
     화학
    1.08
     хими
    1.07
     CHEMICAL
    0.99
    chemical
    0.97
    CHEMICAL
    0.93
     chemically
    0.92
     chem
    0.91
    Activations Density 0.000%

    No Known Activations