© 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. 11464
    Prev
    Next
    INDEX
    Explanations

    words related to a user performing an action, or about people in general.

    oai_token-act-pair · gemini-2.0-flash

    diverse terms and queries related to user actions

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

    People doing something

    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
     Has
    -0.48
    为止
    -0.48
     self
    -0.48
    alors
    -0.47
    Has
    -0.46
    for
    -0.45
    chier
    -0.45
    abetes
    -0.44
     quitt
    -0.43
    Вт
    -0.42
    POSITIVE LOGITS
     to
    1.70
     να
    0.94
     <<<<<<<<<<<<<<
    0.82
    ที่จะ
    0.74
     fallu
    0.72
     للمعارف
    0.71
    ércoles
    0.70
    featureID
    0.66
     Roskov
    0.65
     abzu
    0.63
    Activations Density 10.629%

    No Known Activations