© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15463
    Prev
    Next
    INDEX
    Explanations

    qualifying adjectives, often emotional, especially those relating to a person's character.

    oai_token-act-pair · gemini-2.0-flash

    Negative sentiment

    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
    WithIOException
    -0.90
    BufferException
    -0.75
     estekak
    -0.75
     виправивши
    -0.75
    TestBed
    -0.72
    SourceChecksum
    -0.71
     BrowserModule
    -0.69
    BrowserModule
    -0.69
    GeneratedValue
    -0.68
    AutoScaleMode
    -0.68
    POSITIVE LOGITS
    :✨
    0.54
     par
    0.52
     le
    0.50
     has
    0.49
     Par
    0.46
    yscale
    0.45
     dead
    0.45
    Coordonnées
    0.45
     al
    0.44
     after
    0.40
    Activations Density 0.811%

    No Known Activations