© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178084
    Prev
    Next
    INDEX
    Explanations

    plants growing or needing care

    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_24_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
     colorless
    0.43
     substrates
    0.42
     ("[
    0.40
    substrate
    0.40
    ="...">
    0.39
     substrate
    0.39
    ...>
    0.39
    summ
    0.39
     Pauli
    0.38
     Boud
    0.38
    POSITIVE LOGITS
    ैर्य
    0.45
    ොර
    0.44
     deficient
    0.43
    しまいました
    0.38
     bekommen
    0.38
     genommen
    0.38
    となりました
    0.38
    畜
    0.38
    ewhere
    0.37
    pecting
    0.37
    Activations Density 0.002%

    No Known Activations