© 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. 6088
    Prev
    Next
    INDEX
    Explanations

    terms related to programming, especially Docker, Apple file systems and SQL

    oai_token-act-pair · gemini-2.0-flash

    software and databases

    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
    GEBURTSDATUM
    -0.49
    AutoField
    -0.49
     PENNSYLVANIA
    -0.47
    scriptcase
    -0.46
     مُعرِّف
    -0.46
    không
    -0.46
     continuant
    -0.46
    Tracce
    -0.45
     continúas
    -0.44
    DataPropertyName
    -0.43
    POSITIVE LOGITS
    ).
    
    0.60
    RTEE
    0.59
    ++
    
    0.58
     siihen
    0.57
    )•
    0.55
     ModelExpression
    0.54
    )");
    
    0.54
    ++);
    0.54
    ++)
    
    0.54
    Ops
    0.53
    Activations Density 22.752%

    No Known Activations