© 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. 3810
    Prev
    Next
    INDEX
    Explanations

    Latin names of plants and possibly other organisms

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    UnsafeEnabled
    -1.01
     unknownFields
    -0.91
     المعيارى
    -0.86
    المكان
    -0.82
     utafitiHapana
    -0.78
     FontWeight
    -0.77
     հղումներ
    -0.75
    OrBuilder
    -0.75
     Mote
    -0.74
    tagHelperRunner
    -0.73
    POSITIVE LOGITS
     gestellt
    0.42
    attendre
    0.36
    Hochspringen
    0.36
    pora
    0.35
     au
    0.34
     Körpers
    0.33
     creciendo
    0.33
    XmlAccessType
    0.33
    tienen
    0.32
    sp
    0.32
    Activations Density 1.290%

    No Known Activations