© 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. 6204
    Prev
    Next
    INDEX
    Explanations

    terms related to industrial manufacturing and engineering, especially injection moulding

    oai_token-act-pair · gemini-2.0-flash

    complex manufacturing processes

    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
    __":
    -0.80
    tagHelperRunner
    -0.73
     AssemblyTitle
    -0.66
    __':
    -0.65
     ivelany
    -0.63
    MLLoader
    -0.63
     MANUFACTURING
    -0.62
    WaitGroup
    -0.61
    ագրություններ
    -0.60
     링크
    -0.60
    POSITIVE LOGITS
     gewe
    0.49
     colores
    0.47
    Neutral
    0.47
     Neutral
    0.46
     Garr
    0.44
     neutral
    0.44
     Grand
    0.44
     j
    0.43
    neutral
    0.43
    ETIC
    0.43
    Activations Density 5.128%

    No Known Activations