© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10335
    Prev
    Next
    INDEX
    Explanations

    technical legal terminology and formal reports

    oai_token-act-pair · gemini-2.0-flash

    documents

    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
     reflected
    -1.23
     represented
    -1.20
     indicated
    -1.18
    indicated
    -1.14
    represented
    -1.05
     evidenced
    -1.01
     signified
    -0.98
     implied
    -0.93
     demonstrated
    -0.91
     embodied
    -0.91
    POSITIVE LOGITS
     commissioned
    0.54
     perch
    0.50
     parlant
    0.50
     measuring
    0.48
    redge
    0.48
     slept
    0.47
    measuring
    0.45
     examining
    0.45
     devoted
    0.44
     mentioning
    0.44
    Activations Density 6.770%

    No Known Activations