© 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. 6171
    Prev
    Next
    INDEX
    Explanations

    descriptions of parts and shapes in technical documents

    oai_token-act-pair · gemini-2.0-flash

    words related to openings or gaps

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

    openings and holes

    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
    rungsseite
    -0.68
    EndContext
    -0.63
    حياته
    -0.61
    InstrumentedTest
    -0.57
     dAtA
    -0.54
    fromnode
    -0.54
     мәкал
    -0.53
     ✭✭
    -0.52
    Rhestr
    -0.50
    ंदीखरीदारी
    -0.49
    POSITIVE LOGITS
     opening
    1.73
     openings
    1.73
     holes
    1.70
     hole
    1.70
    opening
    1.52
    holes
    1.49
     Hole
    1.48
     OPENING
    1.48
     Opening
    1.48
    Opening
    1.46
    Activations Density 4.007%

    No Known Activations