© 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. 4831
    Prev
    Next
    INDEX
    Explanations

    the word "scratch"

    oai_token-act-pair · gemini-2.0-flash

    scratch

    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
    <bos>
    -1.09
    Билгалдахарш
    -0.72
    GEBURTSDATUM
    -0.71
    makeConstraints
    -0.70
    '},
    -0.62
    Przypisy
    -0.62
    tagHelperRunner
    -0.60
     userManager
    -0.60
    LabelTagHelper
    -0.59
     løpet
    -0.59
    POSITIVE LOGITS
     lucrative
    0.61
     proven
    0.57
     alike
    0.55
    alate
    0.55
     heavily
    0.55
    czne
    0.54
     highly
    0.54
    pology
    0.54
     equally
    0.54
    UDO
    0.53
    Activations Density 0.818%

    No Known Activations