© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3204
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms.

    oai_token-act-pair · 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
    setVerticalGroup
    -0.37
    StackNavigator
    -0.36
    djangoproject
    -0.35
    enderror
    -0.33
     GIPHY
    -0.33
     linkovi
    -0.32
     Chwiliwch
    -0.32
    й
    -0.32
     Roskov
    -0.32
    webElementXpaths
    -0.31
    POSITIVE LOGITS
    ly
    1.62
    に
    1.42
    了
    1.30
    nya
    1.26
    ness
    1.09
    the
    1.09
    men
    1.07
    ting
    0.99
    mos
    0.99
    man
    0.96
    Activations Density 3.254%

    No Known Activations