© 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. 15849
    Prev
    Next
    INDEX
    Explanations

    sentences describing legal and financial matters

    oai_token-act-pair · gemini-2.0-flash

    filed

    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
     file
    -2.52
     File
    -2.16
     files
    -2.14
     filed
    -2.14
    file
    -2.14
    File
    -2.08
     filing
    -2.08
     FILE
    -1.95
     Files
    -1.92
    FILE
    -1.84
    POSITIVE LOGITS
    awaiter
    0.48
    ANDUM
    0.47
    queo
    0.46
     cuire
    0.45
    CopyWith
    0.43
    (!__
    0.43
     насељу
    0.42
     prender
    0.41
    auk
    0.40
    undi
    0.40
    Activations Density 2.541%

    No Known Activations