© 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
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44027
    Prev
    Next
    INDEX
    Explanations

    carbon cycles, fixation, dioxide

    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_13_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
     WITH
    0.46
    INT
    0.42
     राशियों
    0.41
     McIntosh
    0.41
    CH
    0.40
    ग्वि
    0.40
    FF
    0.40
    蝿
    0.40
     discounts
    0.40
    ATH
    0.39
    POSITIVE LOGITS
    tenham
    0.52
    haram
    0.42
     کئے
    0.42
    tosecond
    0.42
    ambiente
    0.40
    cerer
    0.40
     땅
    0.39
     setColor
    0.39
     علاقے
    0.38
    AsUp
    0.38
    Activations Density 0.023%

    No Known Activations