© 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
    2. Gemma-2-2B
    3. 7-GEMMASCOPE-TRANSCODER-16K
    4. 10004
    Prev
    Next
    INDEX
    Explanations

    code snippets including brackets and some keywords like char and json

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     sal
    -0.54
    /******/
    -0.51
     f
    -0.47
     pro
    -0.47
    #+#
    -0.44
    hede
    -0.44
     extra
    -0.43
     plus
    -0.43
     gal
    -0.43
     fin
    -0.43
    POSITIVE LOGITS
    <bos>
    0.86
     betweenstory
    0.73
    IsMutable
    0.72
    ItemBackground
    0.67
    IUrlHelper
    0.64
     numberOfRows
    0.64
     gynhyrchwyd
    0.63
    aarrggbb
    0.63
     Monfieur
    0.62
     stomat
    0.60
    Activations Density 0.299%

    No Known Activations