© 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. 11333
    Prev
    Next
    INDEX
    Explanations

    words starting with "prop" that don't contain "erty"

    oai_token-act-pair · gemini-2.0-flash

    terms related to "prop" or properties

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

    prop

    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
    cán
    -0.49
    Advanced
    -0.43
    antin
    -0.42
     ta
    -0.42
     red
    -0.41
    inigte
    -0.40
    ikor
    -0.40
    dubbo
    -0.40
    ্ষ
    -0.40
     Advanced
    -0.39
    POSITIVE LOGITS
    +#+#
    0.88
     SwitchCompat
    0.87
     Seeder
    0.78
    Personensuche
    0.77
    IntoConstraints
    0.72
     onAnimation
    0.72
     BorderRadius
    0.69
     виправивши
    0.67
     صوتيه
    0.66
    InjectAttribute
    0.66
    Activations Density 2.091%

    No Known Activations