© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4558
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to business offerings, requirements and manufacturing.

    oai_token-act-pair · gemini-2.0-flash

    technical, code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     يتيمه
    -0.53
    ]")]
    -0.48
     ISNI
    -0.44
     SEDS
    -0.43
     Juno
    -0.39
     Zorn
    -0.39
    ening
    -0.37
     Dawes
    -0.37
     通販
    -0.36
    ssing
    -0.36
    POSITIVE LOGITS
    ρισσότε
    0.66
    etcode
    0.63
    VideoCapture
    0.62
    ImageIO
    0.57
     invokingState
    0.57
    iNdEx
    0.56
     defStyleAttr
    0.56
     Nauk
    0.55
    paddingVertical
    0.55
     $_[
    0.55
    Activations Density 43.239%

    No Known Activations