© 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. 6099
    Prev
    Next
    INDEX
    Explanations

    technical language related to chemical compounds and reactions.

    oai_token-act-pair · gemini-2.0-flash

    chemistry

    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
     سكانية
    -0.77
    endphp
    -0.73
     LUMP
    -0.73
     дописавши
    -0.70
     esternos
    -0.70
    WithIOException
    -0.69
     EconPapers
    -0.67
    tanleria
    -0.67
    tagHelperRunner
    -0.66
    localctx
    -0.66
    POSITIVE LOGITS
    hydroxy
    0.47
    oyl
    0.46
    acyl
    0.46
    mtable
    0.45
    pheny
    0.44
    าย
    0.44
     oxy
    0.43
     carbo
    0.43
    methoxy
    0.43
     hydroxy
    0.42
    Activations Density 23.233%

    No Known Activations