© 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. 39821
    Prev
    Next
    INDEX
    Explanations

    habitat loss

    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
    de
    0.44
    ę
    0.42
    ваются
    0.42
     раствора
    0.40
    ዎታል
    0.40
    ÿ
    0.40
    RoutingModule
    0.39
     reintegr
    0.39
    ρου
    0.39
    ده
    0.38
    POSITIVE LOGITS
    i
    0.47
     clover
    0.43
     ONLY
    0.40
     👍
    0.39
    ي
    0.39
     audioElement
    0.39
    لاك
    0.39
     lar
    0.38
     belangrijke
    0.38
     charmed
    0.38
    Activations Density 0.020%

    No Known Activations