© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14674
    Prev
    Next
    INDEX
    Explanations

    phrases related to evidence and the legal process

    oai_token-act-pair · gemini-2.0-flash

    say "no"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     No
    -2.20
    No
    -1.94
     NO
    -1.62
    NO
    -1.57
     Nos
    -1.32
     Нет
    -1.29
     Nobody
    -1.24
    Nos
    -1.19
     Not
    -1.15
     Nope
    -1.15
    POSITIVE LOGITS
    ंदीखरीदारी
    0.50
    PerformLayout
    0.50
    AddTagHelper
    0.47
     pinulongan
    0.47
    ImageContext
    0.46
    ReusableCell
    0.46
    InstrumentedTest
    0.45
    ]='\
    0.44
    rieved
    0.44
    LEncoder
    0.44
    Activations Density 4.975%

    No Known Activations