© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2220
    Prev
    Next
    INDEX
    Explanations

    the words associated to relation,importance and also components

    oai_token-act-pair · gemini-2.0-flash

    influence or causality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    RTEE
    -0.77
    RegressionTest
    -0.73
    XDECREF
    -0.64
    Viitteet
    -0.63
    ⓧ
    -0.60
    HostException
    -0.57
     kasarigan
    -0.57
    Література
    -0.57
    లాలు
    -0.57
    AlterField
    -0.56
    POSITIVE LOGITS
     թվական
    0.50
     riemp
    0.46
    GraphicsUnit
    0.45
     فريبيس
    0.44
    SceneManagement
    0.43
    mail
    0.43
    Портал
    0.43
    ztal
    0.41
    ಛ
    0.40
     totaled
    0.40
    Activations Density 58.015%

    No Known Activations