© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9295
    Prev
    Next
    INDEX
    Explanations

    the term "New York" or "Kuala Lumpur" or "Los" or "North".

    oai_token-act-pair · gemini-2.0-flash

    occurrences of 'New York'

    np_token-act-pair-logits · gpt-4o-mini

    New

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Q
    -0.46
    V
    -0.41
    kos
    -0.41
    cians
    -0.39
    R
    -0.39
    ons
    -0.39
    al
    -0.38
    pan
    -0.37
    it
    -0.37
    ol
    -0.37
    POSITIVE LOGITS
     виправивши
    1.24
    RenderAtEndOf
    1.02
     تضيفلها
    1.01
    RegistryLite
    0.97
    principalTable
    0.96
    ItemBackground
    0.93
    CloseOperation
    0.92
     kasarigan
    0.90
    Datuak
    0.85
    AndEndTag
    0.85
    Activations Density 0.079%

    No Known Activations