© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6436
    Prev
    Next
    INDEX
    Explanations

    the word "with", and the substring "com"

    oai_token-act-pair · gemini-2.0-flash

    com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Eager
    -0.63
    eclamp
    -0.60
    ãng
    -0.59
     getBase
    -0.59
    UpDown
    -0.56
     purest
    -0.55
     MDL
    -0.55
    awarkan
    -0.54
     modulo
    -0.54
     Inscrivez
    -0.53
    POSITIVE LOGITS
    <bos>
    0.88
     gyhoeddwyd
    0.66
    disposing
    0.58
     have
    0.57
    PDOException
    0.55
    HandleFunc
    0.54
     kasarigan
    0.54
    Šaltiniai
    0.54
     having
    0.54
    copg
    0.53
    Activations Density 1.262%

    No Known Activations