© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13029
    Prev
    Next
    INDEX
    Explanations

    biology and chemistry related terminology and the degree to which the thing is related to a lab test

    oai_token-act-pair · gemini-2.0-flash

    naked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    AddTagHelper
    -0.47
    uerst
    -0.45
    enumii
    -0.45
     Futebol
    -0.45
    pecabezas
    -0.44
    klara
    -0.43
    べた
    -0.41
    unächst
    -0.41
     Unidas
    -0.40
    ,:),
    -0.40
    POSITIVE LOGITS
     Roskov
    0.86
    OGND
    0.84
    Hentet
    0.81
     beginnetje
    0.79
     للاسماء
    0.79
    TypedDataSet
    0.71
     ddelweddau
    0.71
     ویکی‌پدیای
    0.68
     '\\;'
    0.67
    abestanden
    0.66
    Activations Density 3.726%

    No Known Activations