© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141502
    Prev
    Next
    INDEX
    Explanations

    intermolecular forces

    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_46_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
     पीस
    0.42
     eZ
    0.41
    Electro
    0.41
    خاب
    0.41
    oring
    0.40
    ibling
    0.40
     отдыха
    0.40
    햅
    0.39
    til
    0.38
    Happiness
    0.38
    POSITIVE LOGITS
     Dispersion
    0.37
     Conti
    0.36
    ιών
    0.36
    UGS
    0.35
    ूज
    0.35
    γρα
    0.35
    疯
    0.35
    ATC
    0.34
     Leave
    0.34
     Yani
    0.34
    Activations Density 0.001%

    No Known Activations