© 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. 6011
    Prev
    Next
    INDEX
    Explanations

    the word "Ind" followed by other characters

    oai_token-act-pair · gemini-2.0-flash

    Ind

    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
    ativity
    -0.58
    WriteString
    -0.50
    CrossRef
    -0.50
    getSimpleName
    -0.49
    QPalette
    -0.48
    autoconfigure
    -0.47
    AccessorTable
    -0.46
    fährt
    -0.46
    urie
    -0.46
    chyma
    -0.45
    POSITIVE LOGITS
     سكانية
    0.66
    twimg
    0.63
    IndentedString
    0.60
    󠁴
    0.59
     surla
    0.58
     Astral
    0.57
    WaitGroup
    0.57
    LookAnd
    0.55
     exclamation
    0.54
    PreferredItem
    0.54
    Activations Density 0.424%

    No Known Activations