© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7101
    Prev
    Next
    INDEX
    Explanations

    subjective language expressing opinions about situations or people

    oai_token-act-pair · gemini-2.0-flash

    need

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    :✨
    -0.73
    InputBorder
    -0.49
    Erreferentziak
    -0.48
    شاركة
    -0.46
    ließ
    -0.45
    PyObject
    -0.44
    BagLayout
    -0.44
     shall
    -0.43
    Erstellt
    -0.41
    NOSIS
    -0.41
    POSITIVE LOGITS
     need
    2.38
     Need
    2.11
    Need
    2.06
    need
    2.05
     NEED
    1.86
     needs
    1.84
    NEED
    1.74
    needs
    1.69
     Needs
    1.68
     besoin
    1.65
    Activations Density 3.018%

    No Known Activations