© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12836
    Prev
    Next
    INDEX
    Explanations

    words related to questions, especially questions posed to "you"

    oai_token-act-pair · gemini-2.0-flash

    Answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    LookAnd
    -0.61
    UnusedPrivate
    -0.60
    InstanceState
    -0.60
    حوالہ
    -0.54
     AssemblyCulture
    -0.52
    interopRequire
    -0.52
    IntoConstraints
    -0.52
    scriptId
    -0.50
     Normdatei
    -0.47
    Демографія
    -0.45
    POSITIVE LOGITS
     potrivit
    0.60
    middels
    0.59
    ujuk
    0.57
    netje
    0.56
    msgTypes
    0.56
     asiatique
    0.54
     utafitiHapana
    0.53
    MathML
    0.53
     africaine
    0.52
    تقاوى
    0.51
    Activations Density 10.338%

    No Known Activations