© 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. 690
    Prev
    Next
    INDEX
    Explanations

    places, organizations, and governments.

    oai_token-act-pair · gemini-2.0-flash

    news articles

    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
    HostException
    -0.75
    ########.
    -0.73
     виправивши
    -0.69
    Autoritní
    -0.69
    styleType
    -0.68
    InjectMocks
    -0.68
     actionMode
    -0.67
    SBATCH
    -0.67
     defaultstate
    -0.65
     kaynağından
    -0.65
    POSITIVE LOGITS
     pthread
    0.41
    ędzynarod
    0.39
     pan
    0.38
    pthread
    0.35
     Gere
    0.35
    思い
    0.35
    op
    0.33
    //
    0.33
    Населення
    0.33
    Сюжет
    0.32
    Activations Density 2.631%

    No Known Activations