© 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. 13278
    Prev
    Next
    INDEX
    Explanations

    female characters performing actions.

    oai_token-act-pair · gemini-2.0-flash

    erotic texts

    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
    setof
    -0.55
     Pull
    -0.51
    Point
    -0.51
    Pull
    -0.48
     PULL
    -0.48
     otomatig
    -0.47
     WQS
    -0.47
    UserScript
    -0.46
    ="">
    -0.46
    ToListAsync
    -0.45
    POSITIVE LOGITS
    addContainerGap
    0.55
     nahilalakip
    0.51
     vivre
    0.51
    hadiran
    0.50
     nourrir
    0.48
     humains
    0.47
     privées
    0.47
    minecraftforge
    0.47
     amoureux
    0.46
    seamnă
    0.46
    Activations Density 4.638%

    No Known Activations