© 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. 6309
    Prev
    Next
    INDEX
    Explanations

    hyphenated or compound words and foreign words or phrases

    oai_token-act-pair · gemini-2.0-flash

    Association football

    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
    AddTagHelper
    -0.85
    WriteBarrier
    -0.60
    didSet
    -0.59
    BeginContext
    -0.58
    enderror
    -0.56
    migrationBuilder
    -0.56
    asgi
    -0.55
    OCCURRED
    -0.55
     iParam
    -0.54
    UniformLocation
    -0.52
    POSITIVE LOGITS
     CreateTagHelper
    0.55
     sulph
    0.51
    CrossRef
    0.51
    tagHelperRunner
    0.48
    fahan
    0.47
     Ephe
    0.47
    DatabaseError
    0.47
    EMBL
    0.46
    γμα
    0.46
    MAA
    0.46
    Activations Density 0.316%

    No Known Activations