© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10567
    Prev
    Next
    INDEX
    Explanations

    the word "pump" and words starting with "with"

    oai_token-act-pair · gemini-2.0-flash

    pumps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     With
    -0.63
     Without
    -0.59
    RetentionPolicy
    -0.56
     samfun
    -0.55
     Completed
    -0.54
     låg
    -0.53
    With
    -0.53
    Without
    -0.52
     folhe
    -0.52
    ríamos
    -0.52
    POSITIVE LOGITS
     with
    0.60
    devamını
    0.58
    はじめに
    0.57
    SBATCH
    0.55
    WillAppear
    0.54
    aarrggbb
    0.52
     researcher
    0.50
     aged
    0.50
    AnchorStyles
    0.49
    下载附件
    0.49
    Activations Density 0.638%

    No Known Activations