© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 771
    Prev
    Next
    INDEX
    Explanations

    host plant-insect relationships

    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_40_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
     pristup
    0.39
    㺫
    0.39
     veneer
    0.38
     Campo
    0.37
     रिंग
    0.37
     Setter
    0.37
    Winter
    0.36
    ("")]
    0.36
     ساز
    0.35
     propag
    0.35
    POSITIVE LOGITS
    Host
    0.50
     Host
    0.49
     होस्ट
    0.49
    host
    0.49
     host
    0.48
    plant
    0.45
    hosts
    0.44
    HOST
    0.42
    plants
    0.42
     растение
    0.42
    Activations Density 0.017%

    No Known Activations