© 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. 12193
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly disparate instances of notation and terminology

    oai_token-act-pair · gemini-2.0-flash

    "C" three letter words

    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
    EDEFAULT
    -0.39
    mybatisplus
    -0.35
    pielt
    -0.34
    shadowRadius
    -0.34
    ApiProperty
    -0.34
     sabbia
    -0.34
    ńskiej
    -0.33
     Hogarth
    -0.33
     Мексичка
    -0.33
     transfé
    -0.32
    POSITIVE LOGITS
     CCC
    0.96
     CTC
    0.91
     CSC
    0.90
     Ce
    0.90
     CIC
    0.90
     CCS
    0.89
     CAC
    0.89
    CIC
    0.88
     CMC
    0.87
     CEC
    0.86
    Activations Density 22.059%

    No Known Activations