© 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. 196357
    Prev
    Next
    INDEX
    Explanations

    not understand

    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
    试图
    0.49
    ẓ
    0.42
    捍
    0.42
     berusaha
    0.41
     واب
    0.40
    㫻
    0.39
     Abs
    0.39
     пыта
    0.38
     वाइ
    0.38
    iked
    0.37
    POSITIVE LOGITS
     jää
    0.40
     制
    0.39
     Gare
    0.38
     rubbers
    0.37
     находиться
    0.36
     ingredients
    0.36
    ARING
    0.35
    ี่ยง
    0.35
     Newtonian
    0.35
    fois
    0.34
    Activations Density 0.004%

    No Known Activations