© 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. 14448
    Prev
    Next
    INDEX
    Explanations

    mentions of past events or actions

    oai_token-act-pair · gemini-2.0-flash

    past time

    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
    ]";
    -1.03
     myſelf
    -0.93
    ?");
    -0.88
     EnglishChoose
    -0.86
    ?";
    -0.86
    NUMX
    -0.85
    ultuous
    -0.85
    ."</
    -0.82
    PEZ
    -0.81
    hematical
    -0.81
    POSITIVE LOGITS
    ↵↵
    0.88
    .
    0.82
    <eos>
    0.59
    ,
    0.54
    )
    0.52
     -
    0.51
     etc
    0.50
     and
    0.50
     économiques
    0.48
     pinulongan
    0.47
    Activations Density 0.367%

    No Known Activations