© 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. 3478
    Prev
    Next
    INDEX
    Explanations

    "have a" phrases followed by words that describe an effect

    oai_token-act-pair · gemini-2.0-flash

    impact or effect

    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
    ScopeManager
    -0.67
    úgó
    -0.58
    ]]
    -0.56
    Zeneca
    -0.56
    )));
    -0.52
    _;
    -0.51
    ']))
    -0.50
    ]:
    -0.50
    mbic
    -0.49
    mappedBy
    -0.49
    POSITIVE LOGITS
     raiſ
    0.65
     levee
    0.63
     reaſon
    0.61
     pleaſure
    0.60
     uſe
    0.60
     hydrauli
    0.60
     ſtate
    0.59
     ftate
    0.58
     itſelf
    0.58
     Batalla
    0.57
    Activations Density 11.436%

    No Known Activations