© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10317
    Prev
    Next
    INDEX
    Explanations

    conversational confirmations, agreements and discourse markers such as "you know", "yeah", and "well".

    oai_token-act-pair · gemini-2.0-flash

    conversational filler

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ervoor
    -0.50
    ead
    -0.43
    tagHelper
    -0.42
     Or
    -0.42
    weit
    -0.41
     Page
    -0.41
    getCount
    -0.40
     Boy
    -0.40
    AYA
    -0.40
     And
    -0.40
    POSITIVE LOGITS
    SharedDtor
    0.90
    abetes
    0.85
    StoryboardSegue
    0.82
     autorytatywna
    0.81
     NSCoder
    0.79
     StatelessWidget
    0.77
    脚注の使い方
    0.75
     <=",
    0.73
     MonoBehaviour
    0.72
    ########.
    0.71
    Activations Density 0.952%

    No Known Activations