© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12255
    Prev
    Next
    INDEX
    Explanations

    words relating to actions that could/will/should be taken

    oai_token-act-pair · gemini-2.0-flash

    uncertainty, necessity, importance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    קישורים
    -0.55
    MessageTagHelper
    -0.53
    Життєпис
    -0.52
    ipts
    -0.49
    '))
    -0.46
    LookAnd
    -0.46
    ędziesz
    -0.46
    isms
    -0.46
    glycemia
    -0.45
    --)
    -0.45
    POSITIVE LOGITS
    IBOutlet
    0.76
     ویکی‌پدیای
    0.69
    WebElementEntity
    0.67
    setVerticalGroup
    0.66
     resourceCulture
    0.64
     lenker
    0.64
     continúas
    0.56
    IntoConstraints
    0.54
     betweenstory
    0.54
    bootstrapcdn
    0.54
    Activations Density 34.982%

    No Known Activations