© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11259
    Prev
    Next
    INDEX
    Explanations

    words or phrases that indicate importance or significance

    oai_token-act-pair · gemini-2.0-flash

    significant phrases about improvement and collaboration

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     kasarigan
    -0.83
     initComponents
    -0.77
    ########.
    -0.75
    évaluateur
    -0.70
    LookAnd
    -0.70
     externi
    -0.68
    دانشنامهٔ
    -0.68
     Савезне
    -0.66
    onomía
    -0.65
    Vidite
    -0.64
    POSITIVE LOGITS
     ra
    0.50
     Car
    0.50
     way
    0.45
    Absolutely
    0.45
     Ra
    0.45
     mira
    0.45
     springfox
    0.44
    biggest
    0.44
     effect
    0.43
     biggest
    0.43
    Activations Density 0.618%

    No Known Activations