© 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. 11608
    Prev
    Next
    INDEX
    Explanations

    a mix of seemingly random words and pronouns, with some occasional focus on technical terminology or political-leaning words.

    oai_token-act-pair · 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
    SuppressLint
    -0.56
     need
    -0.56
    roek
    -0.48
     works
    -0.48
    works
    -0.47
    GetAxis
    -0.47
    ıştır
    -0.47
     require
    -0.47
    need
    -0.46
    googleapis
    -0.45
    POSITIVE LOGITS
    awtextra
    0.89
     Meksiku
    0.72
     Paglinawan
    0.65
    endphp
    0.65
     TestBed
    0.62
    EndInit
    0.61
    Jeografia
    0.60
     "..\..\..\
    0.59
    NameInMap
    0.59
    addCriterion
    0.59
    Activations Density 4.772%

    No Known Activations