© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4166
    Prev
    Next
    INDEX
    Explanations

    strings of characters delineating structured file headers like emails, code, and academic papers

    oai_token-act-pair · gemini-2.0-flash

    Names

    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
    AutoScale
    -0.51
    ISupport
    -0.50
     defaultstate
    -0.49
    UnusedPrivate
    -0.45
    Попис
    -0.44
     HasFactory
    -0.44
    QMetaType
    -0.44
     fallu
    -0.42
    ImageContext
    -0.42
     esternos
    -0.41
    POSITIVE LOGITS
     Francis
    0.72
     Steven
    0.71
     Rafael
    0.70
     Anthony
    0.69
     Jonathan
    0.68
     Andrew
    0.68
     Justin
    0.68
     Aaron
    0.68
     Stephen
    0.68
     Maurice
    0.68
    Activations Density 34.764%

    No Known Activations