© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9794
    Prev
    Next
    INDEX
    Explanations

    words that convey a sense of obligation or causation

    oai_token-act-pair · gemini-2.0-flash

    Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Vidite
    -0.83
    enderror
    -0.77
     nakalista
    -0.76
     Italijanski
    -0.73
    SequentialGroup
    -0.73
    astify
    -0.70
    contentLoaded
    -0.69
     CanadaChoose
    -0.66
    RTLD
    -0.65
    findpost
    -0.62
    POSITIVE LOGITS
    reactstrap
    0.46
     trương
    0.43
    intosh
    0.43
    μού
    0.43
    utra
    0.42
     megfelelő
    0.42
    orium
    0.41
    numerusform
    0.41
     correspondant
    0.41
     avulla
    0.40
    Activations Density 2.573%

    No Known Activations