© 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
    2. Gemma-3-27B-IT
    3. 47-GEMMASCOPE-2-TRANSCODER-262K
    4. 218989
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    ecido
    0.41
     Light
    0.41
     Colle
    0.40
    Light
    0.39
    霏
    0.39
     light
    0.39
    Application
    0.38
    hara
    0.38
    ifolia
    0.38
     Friends
    0.38
    POSITIVE LOGITS
    кау
    0.39
    ccccn
    0.39
    ᐸ
    0.38
     международ
    0.37
    തെന്നും
    0.37
    ederal
    0.37
     '.</
    0.36
     SEA
    0.36
     درس
    0.35
    seits
    0.35
    Activations Density 0.010%

    No Known Activations