© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196788
    Prev
    Next
    INDEX
    Explanations

    Omniverse programming

    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
    mies
    0.49
    熹
    0.46
     e
    0.43
    𝐲
    0.42
    lug
    0.41
    痞
    0.40
    簱
    0.39
     лу
    0.38
     Tort
    0.38
     Flamingo
    0.37
    POSITIVE LOGITS
     insecure
    0.41
     महाराष्ट
    0.39
     kopi
    0.39
     insecurity
    0.38
    十
    0.38
     Marcel
    0.37
    重ね
    0.37
     ador
    0.37
     Archim
    0.37
     theme
    0.37
    Activations Density 0.032%

    No Known Activations