© 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. 68770
    Prev
    Next
    INDEX
    Explanations

    GET POST

    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
    ifah
    0.39
     irresponsible
    0.38
     nghệ
    0.38
    ോട്
    0.37
    ተኛ
    0.36
     Bxb
    0.35
     леп
    0.35
    ">−</
    0.35
     indulgent
    0.34
     chụp
    0.34
    POSITIVE LOGITS
     pathways
    0.71
     pathway
    0.70
     path
    0.63
     paths
    0.63
    path
    0.62
     Pathways
    0.61
    Pathway
    0.59
     percorso
    0.59
     Pathway
    0.58
    paths
    0.57
    Activations Density 0.000%

    No Known Activations