© 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. 6665
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to analysis, research, and legal proceedings.

    oai_token-act-pair · gemini-2.0-flash

    Study analysis

    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
     analyze
    -2.27
     analysis
    -2.23
     analyses
    -2.22
     analyzed
    -2.22
    Analysis
    -2.19
     Analysis
    -2.19
     analyse
    -2.19
     analyzing
    -2.19
    analy
    -2.17
     analysed
    -2.16
    POSITIVE LOGITS
     fuori
    0.52
     ujednoznacz
    0.51
     Grosso
    0.49
     فريبيس
    0.48
    chengladbach
    0.47
     Whitfield
    0.46
     tupperware
    0.46
     olvides
    0.46
     الرخصة
    0.45
     tempfile
    0.45
    Activations Density 4.297%

    No Known Activations