© 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. 11292
    Prev
    Next
    INDEX
    Explanations

    terms used when discussing vehicle and bicycle repair

    oai_token-act-pair · gemini-2.0-flash

    terms related to programming or error handling

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

    technical product specifications

    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
    mybatisplus
    -0.59
     ſtre
    -0.58
     validamos
    -0.57
     nakalista
    -0.55
     Diſ
    -0.55
     faſt
    -0.53
     diſt
    -0.53
     utafitiHapana
    -0.52
     itſelf
    -0.52
     Etr
    -0.50
    POSITIVE LOGITS
    RegressionTest
    0.62
     onCreateView
    0.61
     if
    0.58
     resourceCulture
    0.58
    URLException
    0.57
    μως
    0.56
     with
    0.55
    verifyException
    0.55
     chamar
    0.54
    SBATCH
    0.52
    Activations Density 4.267%

    No Known Activations