© 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. 142665
    Prev
    Next
    INDEX
    Explanations

    financial news and social

    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
     glBindTexture
    0.44
     COMMUNICATIONS
    0.43
     底
    0.40
     signOut
    0.40
    椅
    0.39
     सामुदायिक
    0.39
     bottoms
    0.38
     Signaling
    0.38
    底
    0.38
     Sign
    0.38
    POSITIVE LOGITS
    Pro
    0.43
     Tum
    0.40
     للت
    0.40
    Tum
    0.39
     Pro
    0.38
    Pup
    0.38
    corpor
    0.38
    Pent
    0.37
    pleo
    0.37
     Plum
    0.37
    Activations Density 0.001%

    No Known Activations