© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10430
    Prev
    Next
    INDEX
    Explanations

    comments praising a handmade card

    oai_token-act-pair · gemini-2.0-flash

    comments, posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     great
    -1.20
    great
    -1.06
     nice
    -1.05
     lovely
    -0.92
     wonderful
    -0.84
    lovely
    -0.82
    nice
    -0.80
    Lovely
    -0.76
     amazing
    -0.75
    Great
    -0.74
    POSITIVE LOGITS
    contentLoaded
    0.73
    RegressionTest
    0.71
     <<<<<<<<<<<<<<
    0.67
    SourceChecksum
    0.60
    ReferenceEquals
    0.57
    IUrlHelper
    0.56
    tidaknya
    0.56
     ***!
    0.54
    onAttach
    0.54
    EditorBrowsable
    0.53
    Activations Density 10.926%

    No Known Activations