© 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. 10924
    Prev
    Next
    INDEX
    Explanations

    words related to ideas, goals, and decisions, sometimes in the context of scientific studies or plans

    oai_token-act-pair · gemini-2.0-flash

    ideas and plans

    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
     were
    -1.61
    Were
    -1.41
     Were
    -1.18
    were
    -1.15
     WERE
    -0.80
    weren
    -0.62
     erau
    -0.60
     furent
    -0.57
     Audiodateien
    -0.56
    memoized
    -0.55
    POSITIVE LOGITS
     was
    0.77
    bootstrapcdn
    0.72
    amaño
    0.65
    èdia
    0.62
    ientí
    0.62
    öszi
    0.58
    ButtonModule
    0.56
    GrantedAuthority
    0.56
    addCriterion
    0.56
    awtextra
    0.55
    Activations Density 1.642%

    No Known Activations