© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5028
    Prev
    Next
    INDEX
    Explanations

    people who need assistance

    oai_token-act-pair · gemini-2.0-flash

    need, needs, needed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     nahilalakip
    -0.67
     estekak
    -0.65
    ousands
    -0.52
    dyti
    -0.51
    ρας
    -0.49
    bala
    -0.49
     Stel
    -0.47
    ssize
    -0.47
     Infórmanos
    -0.47
     pú
    -0.45
    POSITIVE LOGITS
     need
    1.80
     Need
    1.67
    need
    1.64
    Need
    1.59
     NEED
    1.58
     needs
    1.58
    Needs
    1.48
     Needs
    1.47
     needed
    1.45
    needs
    1.41
    Activations Density 1.035%

    No Known Activations