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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35898
    Prev
    Next
    INDEX
    Explanations

    cacti and succulents

    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_11_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
    0
    0.64
     when
    0.64
    when
    0.59
    f
    0.59
    born
    0.57
    p
    0.55
    Born
    0.55
    Mercury
    0.53
     utilisation
    0.52
    Turbo
    0.52
    POSITIVE LOGITS
    ට්
    0.59
     cacti
    0.55
     ⿱
    0.54
     roślin
    0.54
     प्लांट्स
    0.54
    ವಾಡ
    0.53
     ร
    0.53
     plantes
    0.52
    etails
    0.52
     succulents
    0.52
    Activations Density 0.020%

    No Known Activations