© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13751
    Prev
    Next
    INDEX
    Explanations

    abbreviations for proteins and other biological molecules

    oai_token-act-pair · gemini-2.0-flash

    terms related to immunology

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

    immun

    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
    mybatisplus
    -0.70
    @[+][
    -0.51
     padi
    -0.50
     mese
    -0.47
    Jum
    -0.45
     indépend
    -0.44
    roscopic
    -0.44
     {$
    -0.44
    []]
    -0.43
    glPushMatrix
    -0.43
    POSITIVE LOGITS
     immun
    1.05
     Immun
    0.88
     immuno
    0.77
    immun
    0.77
    Immun
    0.77
     inmun
    0.72
     imun
    0.70
     label
    0.66
     positive
    0.66
     labeling
    0.64
    Activations Density 4.083%

    No Known Activations