© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39514
    Prev
    Next
    INDEX
    Explanations

    chemistry molecule nomenclature

    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_11_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
    Waves
    0.52
    Douglas
    0.52
    Hybrid
    0.52
    ectl
    0.51
    Used
    0.50
    Vic
    0.50
    Xia
    0.48
    琬
    0.48
    собенно
    0.48
    Vine
    0.48
    POSITIVE LOGITS
     lieben
    0.55
    riba
    0.53
    noon
    0.51
     matter
    0.50
    anganese
    0.50
    ্তি
    0.49
    res
    0.49
    sum
    0.49
     helfen
    0.49
    rei
    0.49
    Activations Density 0.014%

    No Known Activations