© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 216958
    Prev
    Next
    INDEX
    Explanations

    word endings -en

    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_47_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
    谦
    0.45
    furan
    0.40
    routerProps
    0.38
    mo
    0.37
    iek
    0.37
     hologram
    0.37
     práci
    0.37
     সুবি
    0.37
     altern
    0.36
    ിയത്
    0.36
    POSITIVE LOGITS
     affiliation
    0.41
     বোঝা
    0.38
    mach
    0.38
     wpt
    0.38
     postponed
    0.38
    蕪
    0.37
    ونت
    0.36
    matmul
    0.36
     KJ
    0.36
    argent
    0.36
    Activations Density 0.001%

    No Known Activations