© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 232780
    Prev
    Next
    INDEX
    Explanations

    ground penetrating radar

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     compete
    0.38
     ax
    0.36
    pipes
    0.35
     SOCKET
    0.35
    ches
    0.35
     deleterious
    0.35
     конку
    0.34
    젝
    0.34
    ="./
    0.34
     electrician
    0.34
    POSITIVE LOGITS
    격
    0.42
     Menlo
    0.42
     przyn
    0.40
     demasiado
    0.39
     APIDC
    0.39
    леду
    0.38
    imple
    0.38
     Nası
    0.37
     inv
    0.37
    मान
    0.37
    Activations Density 0.000%

    No Known Activations