© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15827
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and compound names.

    oai_token-act-pair · gemini-2.0-flash

    dashes/parentheses

    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
     censiti
    -0.63
    σθαι
    -0.60
     سكانية
    -0.59
    __':
    -0.57
    ValueStyle
    -0.56
    мужские
    -0.55
     RSSSF
    -0.54
     betweenstory
    -0.54
    /**
    -0.53
    writeFieldEnd
    -0.53
    POSITIVE LOGITS
    carbox
    0.62
    carboxylic
    0.60
    acrylate
    0.58
    urea
    0.57
    ethyl
    0.57
    pyrene
    0.56
    alanine
    0.56
    TiO
    0.55
    ethylene
    0.55
    alkyl
    0.55
    Activations Density 22.667%

    No Known Activations