© 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. 13099
    Prev
    Next
    INDEX
    Explanations

    certain comparative statements based on quantity

    oai_token-act-pair · gemini-2.0-flash

    Comparisons

    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
     themselves
    -0.49
    شوف
    -0.46
    ednes
    -0.44
    leggen
    -0.43
     générations
    -0.41
     not
    -0.41
    ofold
    -0.41
    MessageTagHelper
    -0.41
    țiune
    -0.40
     Creator
    -0.40
    POSITIVE LOGITS
     مشين
    0.92
     <>",
    0.82
    enumi
    0.79
    ConstraintMaker
    0.75
    ]")]
    0.72
    awtextra
    0.71
     ostavi
    0.69
    #+#
    0.68
     postIndex
    0.66
     AssemblyProduct
    0.65
    Activations Density 5.736%

    No Known Activations