© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10791
    Prev
    Next
    INDEX
    Explanations

    words that are commonly used, but not very informative

    oai_token-act-pair · gemini-2.0-flash

    Human resources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ścioła
    -0.56
    ollectionView
    -0.56
     ProtoMessage
    -0.52
     estekak
    -0.50
     []:
    -0.49
    igshid
    -0.49
    Transkript
    -0.46
     sentire
    -0.46
     morire
    -0.45
    ázaro
    -0.45
    POSITIVE LOGITS
     Personnel
    1.32
     personnel
    1.27
    Personnel
    1.21
    personnel
    1.12
     PERSONNEL
    1.10
     human
    1.09
     Human
    1.02
    Human
    1.02
    human
    0.97
    人力
    0.87
    Activations Density 1.676%

    No Known Activations