© 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. 12716
    Prev
    Next
    INDEX
    Explanations

    words related to cells, tissues, and molecular biology

    oai_token-act-pair · gemini-2.0-flash

    cell

    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
     doInBackground
    -0.84
    UnitTesting
    -0.74
    ScopeManager
    -0.69
    ⓧ
    -0.69
    oplayer
    -0.69
    Tikang
    -0.64
    EDEFAULT
    -0.61
    Scénario
    -0.60
    AddTagHelper
    -0.59
    OGND
    -0.58
    POSITIVE LOGITS
    lohy
    0.47
    uly
    0.46
    bibfield
    0.44
     ul
    0.43
     汉
    0.43
     بيها
    0.43
    <bos>
    0.43
    ulted
    0.42
     cycle
    0.42
    bourhood
    0.41
    Activations Density 2.075%

    No Known Activations