© 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. 14871
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of biochemical processes

    oai_token-act-pair · gemini-2.0-flash

    Protein phosphorylation

    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
     Phosph
    -1.43
     phosphory
    -1.38
     phosphorylation
    -1.26
    Phosph
    -1.23
    phosph
    -1.23
     phosph
    -1.17
     Buffer
    -1.13
     Phosphorus
    -1.13
     Phosphate
    -1.10
     Phosp
    -1.09
    POSITIVE LOGITS
    upsert
    0.49
    Arturo
    0.47
    {\$
    0.46
    ípio
    0.45
    Felic
    0.44
     bocca
    0.44
     automne
    0.44
    ộm
    0.43
    stod
    0.42
     îl
    0.41
    Activations Density 3.036%

    No Known Activations