© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11914
    Prev
    Next
    INDEX
    Explanations

    technical scientific terms relating to medicine or biology with a focus on cellular biology and surgical procedures

    oai_token-act-pair · gemini-2.0-flash

    tissue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Tissue
    -1.10
     tissue
    -1.10
    tissue
    -1.02
    Tissue
    -1.02
     tissues
    -0.97
     Tissues
    -0.92
     Gewebe
    -0.65
    tiss
    -0.62
     Root
    -0.57
     root
    -0.56
    POSITIVE LOGITS
    DockStyle
    0.73
     незавершена
    0.62
    BeginContext
    0.61
    nologue
    0.60
     raiſ
    0.60
    Vidite
    0.59
    sidenav
    0.57
    tonsoft
    0.57
    AddHtmlAttribute
    0.56
    FetchType
    0.56
    Activations Density 2.457%

    No Known Activations