© 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. 302
    Prev
    Next
    INDEX
    Explanations

    text describing features or capabilities of some product or model.

    oai_token-act-pair · gemini-2.0-flash

    vehicle models and handling

    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
     autorytatywna
    -0.76
     שוליים
    -0.68
    PointerException
    -0.66
    حياتها
    -0.65
     consultato
    -0.64
    HostException
    -0.59
     JSONException
    -0.57
    gade
    -0.57
     Савезне
    -0.57
    őre
    -0.56
    POSITIVE LOGITS
     qualidade
    0.49
     aérienne
    0.48
    Quality
    0.48
    Calidad
    0.47
    MessageTagHelper
    0.46
     habido
    0.45
     difesa
    0.45
     introduit
    0.45
    #+#
    0.45
    fromnode
    0.44
    Activations Density 3.055%

    No Known Activations