© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14368
    Prev
    Next
    INDEX
    Explanations

    mentions of Poland, municipalities, villages, towns and other political subdivisions.

    oai_token-act-pair · gemini-2.0-flash

    Poland and Peugeot

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Collegamenti
    -0.45
    ALITY
    -0.42
     rada
    -0.40
    <?,
    -0.40
     Genes
    -0.39
    Ena
    -0.39
     pierce
    -0.39
     proti
    -0.38
     joão
    -0.38
     Beale
    -0.38
    POSITIVE LOGITS
     يتيمه
    0.73
    ]")]
    0.73
     propOrder
    0.73
    kuuta
    0.71
    HostException
    0.71
     سكانية
    0.68
     BoxDecoration
    0.68
    unmodifiable
    0.67
     InputDecoration
    0.66
    tableFuture
    0.64
    Activations Density 0.212%

    No Known Activations