© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 280
    Prev
    Next
    INDEX
    Explanations

    nouns and gerunds related to education, processes or events.

    oai_token-act-pair · gemini-2.0-flash

    formal writing

    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
     Anſ
    -0.77
     Theſe
    -0.76
     itſelf
    -0.75
     purpoſe
    -0.73
     beſt
    -0.72
     fubject
    -0.72
     ſche
    -0.71
     himſelf
    -0.71
     Jefus
    -0.70
     ſte
    -0.69
    POSITIVE LOGITS
     "..\..\
    0.50
     disambiguazione
    0.46
    versy
    0.45
    rasser
    0.44
     Савезне
    0.44
    èlement
    0.43
    Autoritní
    0.43
    kháu
    0.42
    цездатний
    0.42
     ple
    0.41
    Activations Density 30.853%

    No Known Activations