© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14223
    Prev
    Next
    INDEX
    Explanations

    a combination of seemingly random strings of characters along with graphical user interface elements in Java code

    oai_token-act-pair · gemini-2.0-flash

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    q
    -0.60
    TM
    -0.54
    peq
    -0.51
    ConstraintMaker
    -0.49
    zy
    -0.49
    cs
    -0.49
    AutoScaleMode
    -0.49
    шня
    -0.48
    be
    -0.48
    dd
    -0.48
    POSITIVE LOGITS
     kasarigan
    0.85
    FormTagHelper
    0.59
     KeyError
    0.56
    NewUrlParser
    0.54
     كومونز
    0.53
    ValueStyle
    0.52
    Parcelize
    0.50
    newArrayList
    0.50
    WithMany
    0.49
     inalámbrica
    0.49
    Activations Density 4.871%

    No Known Activations