© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6449
    Prev
    Next
    INDEX
    Explanations

    words and fragments from Croatian language related to Facebook, email addresses, and user accounts

    oai_token-act-pair · gemini-2.0-flash

    code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     for
    -0.40
    for
    -0.33
     i
    -0.32
     in
    -0.29
    V
    -0.29
    C
    -0.24
    1
    -0.23
     V
    -0.23
    4
    -0.23
     
    -0.22
    POSITIVE LOGITS
     للمعارف
    1.27
    TestingModule
    1.17
    تقاوى
    1.11
     Majefty
    1.10
     فريبيس
    1.09
     gynhyrchwyd
    1.09
     HasFactory
    1.09
     Reſ
    1.08
     ―――――
    1.08
     pleaſure
    1.06
    Activations Density 0.928%

    No Known Activations