© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199169
    Prev
    Next
    INDEX
    Explanations

    bacterial or microbial names

    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_27_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
     recebe
    0.38
     reciben
    0.38
     thụ
    0.37
     отриму
    0.36
     recibirá
    0.35
    }}+\
    0.35
     खूबसूरत
    0.35
     recibieron
    0.35
    மின்றி
    0.34
     तिजारत
    0.34
    POSITIVE LOGITS
     analogies
    0.37
     OBJ
    0.36
    OBJ
    0.36
    Obj
    0.35
     band
    0.35
     analogy
    0.34
    obie
    0.34
    꾹
    0.33
    اق
    0.32
    乐队
    0.32
    Activations Density 0.001%

    No Known Activations