© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1745
    Prev
    Next
    INDEX
    Explanations

    verbs related to progress, prevention, or influence

    oai_token-act-pair · gemini-2.0-flash

    legal language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Izvori
    -0.71
     übersch
    -0.53
     الحره
    -0.52
    WithMany
    -0.52
     مرئيه
    -0.51
     Drilling
    -0.50
    mpz
    -0.50
    </tfoot>
    -0.50
    <!--[
    -0.50
    hidupan
    -0.50
    POSITIVE LOGITS
     confronti
    0.61
     włosy
    0.57
     cdti
    0.57
    MediaStore
    0.56
    бенок
    0.54
    langsung
    0.54
    PyExc
    0.53
    Aims
    0.52
     obtient
    0.52
    working
    0.52
    Activations Density 2.449%

    No Known Activations