© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4922
    Prev
    Next
    INDEX
    Explanations

    place names and related words like "of"

    oai_token-act-pair · gemini-2.0-flash

    New Zealand and Pacific Islands

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    #+#
    -0.92
     الرياضيه
    -0.91
     незавершена
    -0.90
    RenderAtEndOf
    -0.88
    intios
    -0.84
    Попис
    -0.82
    richTextPanel
    -0.79
    StructEnd
    -0.78
    IntoConstraints
    -0.76
     betweenstory
    -0.75
    POSITIVE LOGITS
    Lab
    0.46
    lab
    0.42
    нього
    0.41
    quido
    0.41
    LR
    0.41
    label
    0.40
     m
    0.40
     consenti
    0.38
     ir
    0.38
    ığında
    0.37
    Activations Density 0.257%

    No Known Activations