© 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. 5680
    Prev
    Next
    INDEX
    Explanations

    mentions of heat or highlighting

    oai_token-act-pair · gemini-2.0-flash

    emphasis and heat

    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
     تضيفلها
    -1.02
    styleType
    -0.96
    〢
    -0.84
    ourites
    -0.82
    halation
    -0.80
     متعلقه
    -0.79
    contentLoaded
    -0.79
    WriteBarrier
    -0.78
    -------
    -0.78
    érience
    -0.77
    POSITIVE LOGITS
    _
    0.66
    er
    0.63
    /
    0.54
    #
    0.54
    ol
    0.54
    Local
    0.51
    $
    0.51
    De
    0.51
    Po
    0.50
    Cap
    0.50
    Activations Density 1.034%

    No Known Activations