© 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. 12506
    Prev
    Next
    INDEX
    Explanations

    the word "stage" or words related to trails

    oai_token-act-pair · gemini-2.0-flash

    stage

    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
     betweenstory
    -0.49
     kaikk
    -0.47
     ilmo
    -0.47
    let
    -0.45
    reg
    -0.45
     vähän
    -0.45
     kautta
    -0.42
     stages
    -0.42
     couple
    -0.41
    cl
    -0.41
    POSITIVE LOGITS
    toMatchSnapshot
    0.71
    uttavia
    0.68
    ButterKnife
    0.67
     tartalomajánló
    0.66
     EClass
    0.64
     gespannt
    0.63
    ransition
    0.63
    WEBPACK
    0.63
    GetMapping
    0.62
     nargin
    0.62
    Activations Density 0.310%

    No Known Activations