© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5731
    Prev
    Next
    INDEX
    Explanations

    the word "range"

    oai_token-act-pair · gemini-2.0-flash

    range

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.65
    TimeTo
    -0.46
    '
    -0.44
    bis
    -0.42
    profen
    -0.41
    jupiter
    -0.40
     bis
    -0.39
     Indien
    -0.39
    ടെ
    -0.39
     Indians
    -0.39
    POSITIVE LOGITS
     تضيفلها
    1.05
    ValueStyle
    1.04
     various
    0.91
     many
    0.85
    RenderAtEndOf
    0.81
    цездатний
    0.81
    various
    0.81
     verschied
    0.79
     beragam
    0.79
     énorm
    0.79
    Activations Density 0.165%

    No Known Activations