© 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. 2372
    Prev
    Next
    INDEX
    Explanations

    strings of characters starting with "B" and including "\x000".

    oai_token-act-pair · gemini-2.0-flash

    Code/technical data

    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
    ba
    -0.81
    BA
    -0.76
    Ba
    -0.75
     ba
    -0.75
     Ba
    -0.73
    bar
    -0.71
    bal
    -0.71
    BAR
    -0.69
    BE
    -0.69
    Bar
    -0.69
    POSITIVE LOGITS
    AccessorTable
    0.59
     autorytatywna
    0.52
     브
    0.48
     ब्र
    0.48
    HasForeignKey
    0.48
     Brow
    0.47
    centralwidget
    0.47
     brome
    0.47
     breathe
    0.47
     browns
    0.46
    Activations Density 1.424%

    No Known Activations