© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7022
    Prev
    Next
    INDEX
    Explanations

    descriptions of trails and paths with an emphasis on location

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    UserScript
    -0.63
     surla
    -0.60
    TagMode
    -0.59
    siyah
    -0.55
     main
    -0.54
     ISNI
    -0.52
    PostInfinity
    -0.52
    ölf
    -0.49
     Lös
    -0.48
     parseFrom
    -0.47
    POSITIVE LOGITS
    cektir
    0.63
    RunWith
    0.60
     wireType
    0.55
    ubar
    0.52
     éprou
    0.51
     <<<<<<<<<<<<<<
    0.51
    createStatement
    0.50
    AllowUser
    0.49
     daarvan
    0.49
    WithIOException
    0.49
    Activations Density 3.235%

    No Known Activations