© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13705
    Prev
    Next
    INDEX
    Explanations

    HTML markup tags and bolded text

    oai_token-act-pair · gemini-2.0-flash

    HTML bolding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    erli
    -0.60
     متعلقه
    -0.59
     AppModule
    -0.59
    scalatest
    -0.58
    ]='\
    -0.57
    uteness
    -0.57
    mapStateToProps
    -0.57
    colades
    -0.56
    ullen
    -0.56
     ͜ʖ
    -0.56
    POSITIVE LOGITS
    <bos>
    1.49
    <?
    0.58
    </strong>
    0.58
    </b>
    0.57
     prossima
    0.53
     réglable
    0.51
     Meksiku
    0.51
     fören
    0.50
     يتيمه
    0.49
     gård
    0.47
    Activations Density 0.951%

    No Known Activations