© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13710
    Prev
    Next
    INDEX
    Explanations

    place names or words which are parts of place names.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    PARIS
    -0.65
    paksa
    -0.63
    سطس
    -0.63
     ירושלים
    -0.61
    WAUKEE
    -0.60
     vettoriale
    -0.58
    obiety
    -0.57
     الدولى
    -0.56
    ronesia
    -0.56
    MADRID
    -0.56
    POSITIVE LOGITS
    GHIJKLM
    0.49
     Fitz
    0.48
    loadModel
    0.45
    interopRequire
    0.45
     Савезне
    0.44
    zeczy
    0.43
     Gamb
    0.42
     deepcopy
    0.42
    kits
    0.42
     nonatomic
    0.42
    Activations Density 3.701%

    No Known Activations