© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12823
    Prev
    Next
    INDEX
    Explanations

    research texts referencing substances, experiments, and/or other published research

    oai_token-act-pair · gemini-2.0-flash

    Chemistry/scientific studies

    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
    Not in Any Lists

    No Comments

    Negative Logits
     vérit
    -0.70
     HasFactory
    -0.65
    VIAF
    -0.61
     plais
    -0.60
     فريبيس
    -0.59
     remarqu
    -0.59
    InstanceState
    -0.57
     aveug
    -0.57
    textTheme
    -0.56
     vœux
    -0.56
    POSITIVE LOGITS
     containing
    0.59
     together
    0.59
     ✭✭
    0.54
     followed
    0.51
    ++;
    0.51
     contains
    0.50
    mazoo
    0.50
    nians
    0.50
    ++;
    0.49
    GetEnumerator
    0.49
    Activations Density 10.674%

    No Known Activations