© 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. 11416
    Prev
    Next
    INDEX
    Explanations

    questions about where and when to take an exam and how to apply

    oai_token-act-pair · gemini-2.0-flash

    tokens related to exam interactions

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

    Code/instructions

    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
     désolés
    -0.76
     MainAxisSize
    -0.74
    ))));
    -0.72
     kleid
    -0.72
     vectorstock
    -0.71
     crdi
    -0.71
    )))));
    -0.71
    __":
    -0.69
     Majefty
    -0.69
     ←
    -0.68
    POSITIVE LOGITS
    loon
    0.49
     per
    0.48
     comp
    0.47
     O
    0.47
     Sol
    0.45
     sol
    0.44
    lijkse
    0.44
     we
    0.44
     f
    0.44
    here
    0.44
    Activations Density 0.477%

    No Known Activations