© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13254
    Prev
    Next
    INDEX
    Explanations

    words that have positive, humanistic, emotional or spiritual connotations.

    oai_token-act-pair · gemini-2.0-flash

    narrative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     transfieras
    -0.61
    esteld
    -0.56
     jScrollPane
    -0.55
    fige
    -0.52
    #+#
    -0.52
    MigrationBuilder
    -0.51
     transférez
    -0.50
     officio
    -0.50
     AssemblyVersion
    -0.50
    ותר
    -0.50
    POSITIVE LOGITS
    
    0.63
    tonsoft
    0.62
     متعلقه
    0.61
     Phry
    0.57
     chroma
    0.56
     Inscrivez
    0.54
     morire
    0.54
     ferrite
    0.54
     quadrat
    0.52
     draught
    0.51
    Activations Density 1.453%

    No Known Activations