© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10333
    Prev
    Next
    INDEX
    Explanations

    things that are often grouped together

    oai_token-act-pair · gemini-2.0-flash

    lessons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    findpost
    -0.93
     kasarigan
    -0.92
     auroit
    -0.91
     feroit
    -0.91
     étoit
    -0.85
     שוליים
    -0.85
    Hauptartikel
    -0.84
     étoient
    -0.84
     avoient
    -0.84
     ainfi
    -0.83
    POSITIVE LOGITS
     
    0.56
    MeasureSpec
    0.52
    '
    0.47
     and
    0.46
    -
    0.43
    1
    0.42
    abilia
    0.42
    3
    0.41
     shabby
    0.40
    ↵
    0.39
    Activations Density 2.546%

    No Known Activations