© 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. 4655
    Prev
    Next
    INDEX
    Explanations

    the word "with" used in conjunction with chemical or monetary amounts

    oai_token-act-pair · gemini-2.0-flash

    addition

    np_max-act · 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
     varandra
    -0.70
     prêts
    -0.65
     komende
    -0.63
    />";
    -0.62
     igång
    -0.62
     =",
    -0.60
    berdayakan
    -0.60
     larmes
    -0.58
     meubles
    -0.57
    ])]
    -0.57
    POSITIVE LOGITS
    <bos>
    1.91
     Plus
    0.70
    '
    0.69
    +
    0.69
     plus
    0.69
    ’
    0.68
    Plus
    0.67
    plus
    0.61
     w
    0.60
    w
    0.59
    Activations Density 1.924%

    No Known Activations