© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10545
    Prev
    Next
    INDEX
    Explanations

    scientific texts related to biology or neurology, specifically mentioning hormones, brain function, and/or mental health

    oai_token-act-pair · gemini-2.0-flash

    biological terms related to anatomy

    np_token-act-pair-logits · gpt-4o-mini

    Biological terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    таратура
    -0.59
     uitges
    -0.58
    ագրություններ
    -0.49
    
    -0.46
    enterOuterAlt
    -0.46
    '][]
    -0.46
    '])->
    -0.46
    بوابة
    -0.46
     nahilalakip
    -0.46
    shim
    -0.45
    POSITIVE LOGITS
     bones
    1.14
     bone
    1.13
     DNA
    0.97
     gene
    0.93
    bone
    0.91
     muscle
    0.89
     protein
    0.84
    bones
    0.84
     Bone
    0.83
     neuron
    0.83
    Activations Density 4.778%

    No Known Activations