© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8484
    Prev
    Next
    INDEX
    Explanations

    code file headers

    oai_token-act-pair · gemini-2.0-flash

    rights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    RegressionTest
    -0.57
    <bos>
    -0.54
    äng
    -0.38
    lat
    -0.38
    uc
    -0.36
    ""
    -0.36
     kos
    -0.36
    нен
    -0.36
    insert
    -0.36
    Tag
    -0.36
    POSITIVE LOGITS
    TemporalType
    0.66
     defaultstate
    0.65
    RenderAtEndOf
    0.65
    Tazama
    0.65
    XmlAccessType
    0.65
     BoxFit
    0.65
    AddTagHelper
    0.61
    تقاوى
    0.60
     Roskov
    0.60
     GenerationType
    0.59
    Activations Density 0.290%

    No Known Activations