© 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. 11265
    Prev
    Next
    INDEX
    Explanations

    directional words and phrases

    oai_token-act-pair · gemini-2.0-flash

    phrases related to positions or directions

    np_token-act-pair-logits · gpt-4o-mini

    sides and opposites

    np_max-act-logits · gemini-2.0-flash
    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
     makeStyles
    -0.58
     jspb
    -0.54
     مرئيه
    -0.54
    åringen
    -0.51
    脚注の使い方
    -0.49
     tuyo
    -0.48
     kasarigan
    -0.47
     Drapeau
    -0.47
     tuong
    -0.46
    zsef
    -0.46
    POSITIVE LOGITS
     lane
    0.80
     wing
    0.70
    EndProject
    0.67
     half
    0.66
    Jereo
    0.65
     end
    0.64
     strand
    0.63
    Xna
    0.62
     axis
    0.61
     surla
    0.61
    Activations Density 3.501%

    No Known Activations