© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7339
    Prev
    Next
    INDEX
    Explanations

    words related to community service, charity, environmental advocacy and children.

    oai_token-act-pair · gemini-2.0-flash

    negation

    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
     autorytatywna
    -1.00
    DockStyle
    -0.93
     EconPapers
    -0.79
    ConstraintMaker
    -0.77
     مرئيه
    -0.73
     Chwiliwch
    -0.73
    ifrance
    -0.69
    原始内容存档于
    -0.69
     transfieras
    -0.66
    EDEFAULT
    -0.65
    POSITIVE LOGITS
     non
    2.45
    Non
    2.30
     Non
    2.20
    non
    2.19
     NON
    1.98
    NON
    1.96
    非
    1.71
     非
    1.52
     Nicht
    1.36
     icke
    1.35
    Activations Density 4.570%

    No Known Activations