© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14936
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "Mod" as well as words in which "mod" is the prefix

    oai_token-act-pair · gemini-2.0-flash

    Mod

    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
    ỏi
    -0.50
    日语
    -0.46
     Ross
    -0.45
    BACKEND
    -0.42
    רצ
    -0.41
     jog
    -0.40
     skal
    -0.39
     oss
    -0.39
     тор
    -0.38
    ξε
    -0.38
    POSITIVE LOGITS
    IUrlHelper
    0.75
    RegressionTest
    0.67
     Савезне
    0.67
    ThroughAttribute
    0.66
    featureID
    0.66
     pleaſure
    0.61
    alities
    0.60
    σθαι
    0.60
    الدراسه
    0.59
    inea
    0.59
    Activations Density 0.706%

    No Known Activations