© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11895
    Prev
    Next
    INDEX
    Explanations

    code fragments in various computer languages

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     récentes
    -0.12
     démocr
    -0.11
     esquer
    -0.08
     religieuses
    -0.06
     giuri
    -0.06
     laterale
    -0.06
     attentes
    -0.05
    retudo
    -0.05
     fédé
    -0.04
     filós
    -0.02
    POSITIVE LOGITS
    }{*}{}
    1.09
     CURIAM
    1.08
    </tfoot>
    1.08
    HasForeignKey
    1.07
    ResumeLayout
    1.07
    EDEFAULT
    1.06
    AddTagHelper
    1.06
    Geplaatst
    1.04
    {}",
    1.04
    <unused53>
    1.02
    Activations Density 3.757%

    No Known Activations