© 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. 3750
    Prev
    Next
    INDEX
    Explanations

    tokens which begin with a '.' character, code markup and parts of names

    oai_token-act-pair · gemini-2.0-flash

    Analysis, explanations

    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
     dead
    -0.63
     flat
    -0.62
     wind
    -0.61
     grass
    -0.60
     rain
    -0.60
     wings
    -0.59
     dirt
    -0.59
     dry
    -0.58
     beaten
    -0.57
     smokes
    -0.56
    POSITIVE LOGITS
     analysis
    1.01
     description
    0.96
     explanation
    0.92
     review
    0.89
     information
    0.88
     discussion
    0.87
     presentation
    0.85
     application
    0.85
     definition
    0.85
    description
    0.84
    Activations Density 10.870%

    No Known Activations