© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6514
    Prev
    Next
    INDEX
    Explanations

    code snippets or markup, especially those involving loops and matrix operations

    oai_token-act-pair · gemini-2.0-flash

    columns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     terre
    -0.57
     Length
    -0.52
     FetchType
    -0.51
     shortening
    -0.50
     licensee
    -0.49
    Length
    -0.49
    "}")
    -0.47
    short
    -0.46
    ագրություններ
    -0.46
    length
    -0.46
    POSITIVE LOGITS
     columns
    1.54
     column
    1.48
     Column
    1.24
    column
    1.20
     Columns
    1.19
     COLUMN
    1.16
    columns
    1.13
     colonne
    1.13
     colonnes
    1.12
    Column
    1.09
    Activations Density 1.298%

    No Known Activations