© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203545
    Prev
    Next
    INDEX
    Explanations

    chemical reaction formulas

    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_12_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
    st
    0.51
    bird
    0.50
    br
    0.48
    removal
    0.46
    RL
    0.46
    лябин
    0.46
    5
    0.46
    byte
    0.45
    plus
    0.44
    molecule
    0.44
    POSITIVE LOGITS
     đựng
    0.58
     INKA
    0.55
     với
    0.55
     N
    0.54
     paprika
    0.53
     financiero
    0.53
     resalt
    0.52
     Taurus
    0.52
     Deportivo
    0.52
     Wraith
    0.52
    Activations Density 0.002%

    No Known Activations