© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4761
    Prev
    Next
    INDEX
    Explanations

    seemingly different things: the word "phase" in the context of electrical engineering, seemingly random numbers, and discrete cosine transforms

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    intenance
    -0.73
    colourful
    -0.71
    \]
    -0.71
    ighbor
    -0.71
    URDAY
    -0.70
    PEAT
    -0.69
    tawan
    -0.68
    troppo
    -0.68
    χυ
    -0.68
    Amicalement
    -0.68
    POSITIVE LOGITS
    <bos>
    1.82
    I
    0.77
     initComponents
    0.68
    from
    0.65
    The
    0.64
    A
    0.64
    B
    0.63
    H
    0.61
    '
    0.59
    My
    0.57
    Activations Density 0.669%

    No Known Activations