© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173714
    Prev
    Next
    INDEX
    Explanations

    evergreen, perennial, recurring, annual, consistent

    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_20_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
     plantings
    0.51
    ᴊ
    0.49
     තම
    0.48
    🛴
    0.45
     tumbuhan
    0.44
    ുകൂ
    0.44
     będzie
    0.44
     vajj
    0.44
    damageCount
    0.43
    핳
    0.43
    POSITIVE LOGITS
     well
    0.45
     Manuscript
    0.41
    流行
    0.38
     annually
    0.38
     вс
    0.37
     Investigation
    0.37
     annual
    0.37
     long
    0.36
     imposes
    0.36
    浮
    0.36
    Activations Density 0.019%

    No Known Activations