© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7784
    Prev
    Next
    INDEX
    Explanations

    tokens associated with scientific research and legal cases

    oai_token-act-pair · gemini-2.0-flash

    Scientific experiments

    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
     were
    -2.78
    Were
    -2.50
     Were
    -2.30
    were
    -2.28
     WERE
    -1.97
     weren
    -1.70
     були
    -1.33
     były
    -1.27
     voltak
    -1.25
    weren
    -1.23
    POSITIVE LOGITS
    GeneratedCode
    0.61
    landen
    0.57
     NavController
    0.55
    hoven
    0.53
    ConstraintMaker
    0.50
    __()
    0.49
    erol
    0.49
    ément
    0.49
    ulongan
    0.48
    iaceae
    0.48
    Activations Density 5.222%

    No Known Activations