© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8808
    Prev
    Next
    INDEX
    Explanations

    the strings "Gal", "Glu", or "gal" related to the drug Galafold and chemical compounds

    oai_token-act-pair · gemini-2.0-flash

    Gal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     resourceCulture
    -0.87
    ########.
    -0.83
    twimg
    -0.79
    DataAnnotations
    -0.76
     &___
    -0.70
    Personendaten
    -0.68
     szóci
    -0.66
     henvisninger
    -0.65
    afficheront
    -0.65
    ngdoc
    -0.65
    POSITIVE LOGITS
    zing
    0.50
    acherous
    0.45
    genstein
    0.44
    vans
    0.44
     Br
    0.43
     unbekannt
    0.43
    Br
    0.41
    fetera
    0.40
    umns
    0.40
    ğren
    0.39
    Activations Density 1.203%

    No Known Activations