© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7637
    Prev
    Next
    INDEX
    Explanations

    language associated with formal speeches or reports

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     speaking
    -1.13
     saying
    -0.94
     commenting
    -0.90
     mentioning
    -0.87
     pointing
    -0.86
    speaking
    -0.85
     addressing
    -0.84
     citing
    -0.82
     quoting
    -0.82
     referring
    -0.82
    POSITIVE LOGITS
    ValueStyle
    0.48
     St
    0.47
    DATABASES
    0.47
    것
    0.47
    jednoc
    0.46
    St
    0.46
     ultimi
    0.45
    것은
    0.45
    }{-
    0.44
    aceite
    0.44
    Activations Density 5.016%

    No Known Activations