© 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. 9732
    Prev
    Next
    INDEX
    Explanations

    positive and thoughtful sentiment expressing care and detail

    oai_token-act-pair · gemini-2.0-flash

    thinking

    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
    KURZBESCHREIBUNG
    -0.56
     Paglinawan
    -0.54
    CWE
    -0.50
    InjectAttribute
    -0.48
    المكان
    -0.47
     automatiquement
    -0.47
     affari
    -0.45
     terap
    -0.44
     puis
    -0.43
     greifen
    -0.43
    POSITIVE LOGITS
     thought
    2.72
    thought
    2.30
     Thought
    2.27
    Thought
    2.23
     THOUGHT
    2.00
     thinking
    1.54
     Think
    1.45
     think
    1.45
    Think
    1.38
    thinking
    1.38
    Activations Density 1.870%

    No Known Activations