© 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. 13806
    Prev
    Next
    INDEX
    Explanations

    references to things, people, objects, or animals that are part of a set of items.

    oai_token-act-pair · 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
    ritch
    -0.80
    giant
    -0.71
    Huge
    -0.68
    huge
    -0.67
     Bizarre
    -0.66
     Huge
    -0.66
     giant
    -0.65
    GenerationType
    -0.65
    uría
    -0.65
     gigantic
    -0.65
    POSITIVE LOGITS
     ſee
    0.47
    awtextra
    0.47
     be
    0.46
     ſhe
    0.46
    cartas
    0.45
    PreAuthorize
    0.44
     over
    0.44
    addGap
    0.43
     wok
    0.43
     avoit
    0.42
    Activations Density 8.004%

    No Known Activations