© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4184
    Prev
    Next
    INDEX
    Explanations

    the word "fancy"

    oai_token-act-pair · gemini-2.0-flash

    fancy

    np_max-act · gemini-2.0-flash

    fancy

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ↵↵
    -1.09
    A
    -0.84
    a
    -0.84
    <strong>
    -0.82
    the
    -0.80
    The
    -0.79
    <b>
    -0.78
    An
    -0.73
    <eos>
    -0.72
     
    -0.71
    POSITIVE LOGITS
    olesale
    1.06
    medriver
    0.98
    guiente
    0.94
    /−
    0.94
    ymce
    0.92
    glGen
    0.88
     BoxFit
    0.84
    ValueStyle
    0.84
    eſt
    0.83
     iſt
    0.83
    Activations Density 1.746%

    No Known Activations