© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3274
    Prev
    Next
    INDEX
    Explanations

    the word "rest" and its various forms

    oai_token-act-pair · gemini-2.0-flash

    the word "rest" and variations of it

    np_token-act-pair-logits · gpt-4o-mini

    rest

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    rrggbb
    -0.68
     RouterModule
    -0.59
     Pern
    -0.56
     Paglinawan
    -0.54
    mapStateToProps
    -0.54
     Italijani
    -0.53
    PORTER
    -0.53
    حياته
    -0.52
     terecht
    -0.51
    SequentialGroup
    -0.51
    POSITIVE LOGITS
    tagHelper
    0.47
    ✨:
    0.44
    ora
    0.44
    utar
    0.43
     sumpay
    0.41
    platz
    0.41
     físico
    0.41
     povr
    0.40
    urin
    0.40
    --;
    0.40
    Activations Density 2.237%

    No Known Activations