© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5518
    Prev
    Next
    INDEX
    Explanations

    code or legal jargon initials and acronyms

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    HtmlAttribute
    -0.49
     residente
    -0.49
     naselje
    -0.41
    Pont
    -0.39
    Piper
    -0.38
    PageFactory
    -0.37
     Nauk
    -0.37
    狸
    -0.36
     samarbeid
    -0.36
     Pru
    -0.35
    POSITIVE LOGITS
    ThroughAttribute
    0.87
    ########.
    0.73
    -------------</
    0.70
     lenker
    0.66
     批
    0.62
     doInBackground
    0.60
    رشف
    0.60
     createState
    0.59
    >--}}
    0.59
     "..\..\
    0.59
    Activations Density 0.614%

    No Known Activations