© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3167
    Prev
    Next
    INDEX
    Explanations

    instructional verbiage in recipes.

    oai_token-act-pair · gemini-2.0-flash

    Cutting related actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Roskov
    -0.71
     متعلقه
    -0.68
    SequentialGroup
    -0.66
    ImageContext
    -0.65
     nakalista
    -0.63
    ंदीखरीदारी
    -0.58
     StringTokenizer
    -0.57
     onCreateView
    -0.57
     breaking
    -0.56
    ::_('
    -0.56
    POSITIVE LOGITS
     scurt
    0.47
     extensão
    0.46
     cantit
    0.46
    apkan
    0.46
     Zeller
    0.45
    INUM
    0.44
     fondi
    0.44
     libertà
    0.44
     théorie
    0.43
     creș
    0.43
    Activations Density 1.554%

    No Known Activations