© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13512
    Prev
    Next
    INDEX
    Explanations

    phrases that appear to mark shifts in topic or location, as well as related keywords and sentiment.

    oai_token-act-pair · gemini-2.0-flash

    Informal conversation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     unknownFields
    -1.02
     betweenstory
    -0.86
     tartalomajánló
    -0.85
    findpost
    -0.84
    RegressionTest
    -0.83
    ########.
    -0.82
    abestanden
    -0.82
    EditorBrowsable
    -0.80
    expandindo
    -0.80
     متعلقه
    -0.78
    POSITIVE LOGITS
     
    0.53
    pp
    0.50
    ↵
    0.50
    ·
    0.48
    •
    0.47
     —
    0.46
    o
    0.46
    '
    0.45
    ’
    0.45
     mix
    0.45
    Activations Density 1.531%

    No Known Activations