© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 38-GEMMASCOPE-2-TRANSCODER-262K
    4. 838
    Prev
    Next
    INDEX
    Explanations

    pure relationship and pigment

    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_38_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
     Kers
    0.42
    ville
    0.40
     Wer
    0.39
    hasilan
    0.37
    神的
    0.36
    仆
    0.35
    atherine
    0.35
     collects
    0.34
    长的
    0.34
     банков
    0.34
    POSITIVE LOGITS
     pure
    0.88
    Pure
    0.85
    pure
    0.84
     Pure
    0.82
    纯
    0.79
    純
    0.75
     puro
    0.69
    PURE
    0.69
     pura
    0.68
     純
    0.66
    Activations Density 0.020%

    No Known Activations