© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4259
    Prev
    Next
    INDEX
    Explanations

    the organization of a paper and what will be shown

    oai_token-act-pair · gemini-2.0-flash

    follows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     du
    -0.44
     s
    -0.41
     bin
    -0.40
     fit
    -0.40
     S
    -0.40
    fit
    -0.40
     sal
    -0.39
    (
    -0.38
     R
    -0.38
     model
    -0.38
    POSITIVE LOGITS
    MigrationBuilder
    1.03
    ValueStyle
    0.94
    ########.
    0.89
    webElementXpaths
    0.85
    rrggbb
    0.85
     iNdEx
    0.84
    ConstraintMaker
    0.84
    IntoConstraints
    0.82
     kasarigan
    0.82
     itſelf
    0.82
    Activations Density 0.044%

    No Known Activations