© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90081
    Prev
    Next
    INDEX
    Explanations

    Poland, past tense, residence permits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
    Poland
    0.60
    t
    0.60
    Polish
    0.59
     Szcz
    0.59
    tura
    0.59
     Pologne
    0.57
    tempo
    0.57
    즈
    0.56
    iany
    0.56
    July
    0.55
    POSITIVE LOGITS
     MOSFET
    0.58
     deemed
    0.57
    FreeFlag
    0.56
     CONTROL
    0.55
     Kindern
    0.55
    те
    0.55
     trabal
    0.55
    عل
    0.55
    ラル
    0.55
     sandal
    0.54
    Activations Density 0.017%

    No Known Activations