© 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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1340
    Prev
    Next
    INDEX
    Explanations

    words that are related to a physical collection of media such as a boxed set or multi disc set

    oai_token-act-pair · gemini-2.0-flash

    DVD/Blu-ray sets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    KommentareTeilen
    -0.56
    énario
    -0.52
    Espèce
    -0.45
    copyWith
    -0.44
     getProperty
    -0.43
    廓
    -0.43
     teaming
    -0.42
     排
    -0.41
    становка
    -0.41
     pharynx
    -0.41
    POSITIVE LOGITS
     lenker
    0.77
     ModelExpression
    0.70
    Hozzáférés
    0.64
    帖最后由
    0.62
    FunctionFlags
    0.60
     Normdatei
    0.60
    RegistryLite
    0.60
     تانيه
    0.59
     CreateTagHelper
    0.58
    isso
    0.57
    Activations Density 0.272%

    No Known Activations