© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13868
    Prev
    Next
    INDEX
    Explanations

    the name David

    oai_token-act-pair · gemini-2.0-flash

    David

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    rungsseite
    -0.98
     متعلقه
    -0.85
    AndEndTag
    -0.80
    prüche
    -0.80
    #+#
    -0.68
     betweenstory
    -0.65
    siasme
    -0.65
    riwal
    -0.64
    tonode
    -0.62
     فريبيس
    -0.60
    POSITIVE LOGITS
     ModelExpression
    0.44
    viewDidLoad
    0.44
    AsUp
    0.43
    greenrobot
    0.43
    )(((
    0.43
    CopyWith
    0.42
    *)((
    0.42
    windowFixed
    0.42
     utilis
    0.41
     "");
    0.40
    Activations Density 0.220%

    No Known Activations