© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2269
    Prev
    Next
    INDEX
    Explanations

    mentions of the need for more research or analysis.

    oai_token-act-pair · gemini-2.0-flash

    calling for future research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     need
    -2.95
    need
    -2.70
     Need
    -2.58
    Need
    -2.53
     needs
    -2.22
     NEED
    -2.14
     Needs
    -2.05
    needs
    -2.02
    NEED
    -2.00
    Needs
    -1.95
    POSITIVE LOGITS
     Nio
    0.53
    ExecuteReader
    0.49
    ωση
    0.49
    BindingSource
    0.49
    LEncoder
    0.49
    tamento
    0.48
     OnTriggerEnter
    0.48
    ubri
    0.47
     Bancroft
    0.47
    dillos
    0.47
    Activations Density 3.183%

    No Known Activations