© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11188
    Prev
    Next
    INDEX
    Explanations

    the word "so" and sometimes the words "too" or "am" near "so."

    oai_token-act-pair · gemini-2.0-flash

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     viewDidLoad
    -0.59
     WaitForSeconds
    -0.57
     McInt
    -0.57
    AnchorStyles
    -0.55
    MenuInflater
    -0.54
     Merk
    -0.53
    msgSender
    -0.50
     Tade
    -0.50
    itemBuilder
    -0.49
    ]")]
    -0.49
    POSITIVE LOGITS
    beten
    0.58
    MigrationBuilder
    0.58
    ">//
    0.56
     الحره
    0.54
     Personalis
    0.53
    ніципа
    0.52
     baan
    0.52
    GEBURTSDATUM
    0.52
     Meksiku
    0.51
     saja
    0.51
    Activations Density 1.722%

    No Known Activations