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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62773
    Prev
    Next
    INDEX
    Explanations

    landscaping and gardens

    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_41_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
    acetate
    0.40
     Hale
    0.38
     acetate
    0.37
     dilutions
    0.37
     Siv
    0.35
     생산
    0.35
    Rose
    0.35
    썩
    0.34
     Julia
    0.34
    ække
    0.34
    POSITIVE LOGITS
     landscaping
    1.73
     landsc
    1.41
     landscaped
    1.35
     landscape
    1.30
    Landscape
    1.23
     Landscape
    1.20
    landscape
    1.13
     jardins
    1.06
     landscapes
    1.05
     gardens
    1.04
    Activations Density 0.002%

    No Known Activations