© 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. 10825
    Prev
    Next
    INDEX
    Explanations

    text asking for donations or tips

    oai_token-act-pair · gemini-2.0-flash

    tip

    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
    IVEREF
    -0.59
    rrggbb
    -0.59
    SerializedSize
    -0.57
    ConstraintMaker
    -0.57
    LookAnd
    -0.57
     plomb
    -0.53
     psychosis
    -0.53
    expandindo
    -0.52
     EconPapers
    -0.52
    IGraphics
    -0.52
    POSITIVE LOGITS
     tip
    2.45
     tips
    2.30
     Tip
    2.13
    tip
    2.08
    Tip
    2.08
     tipped
    2.00
    tips
    1.91
     Tips
    1.88
     TIP
    1.84
    Tips
    1.82
    Activations Density 2.074%

    No Known Activations