© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9903
    Prev
    Next
    INDEX
    Explanations

    mentions of Italian people, places, or language in text about mathematics or agriculture

    oai_token-act-pair · gemini-2.0-flash

    Italian names and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     *)__
    -0.59
    nikova
    -0.55
     WK
    -0.54
     EconPapers
    -0.54
     Ka
    -0.54
     MK
    -0.53
     JK
    -0.53
     ویکی‌آمباردا
    -0.52
    ]")]
    -0.52
    RenderAtEndOf
    -0.52
    POSITIVE LOGITS
     jegy
    0.55
     helyez
    0.49
     tevé
    0.49
     érté
    0.48
     enged
    0.48
     szerző
    0.48
     vált
    0.48
     talál
    0.48
    Aspect
    0.47
     ögon
    0.47
    Activations Density 3.341%

    No Known Activations