© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5478
    Prev
    Next
    INDEX
    Explanations

    mathematical or statistical equations, plus related notation and vocabulary

    oai_token-act-pair · gemini-2.0-flash

    Code and Calculations

    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
     arşivlendi
    -0.77
     nakalista
    -0.71
     numberOfRows
    -0.69
     Audiodateien
    -0.60
     StringTokenizer
    -0.60
     للتو
    -0.59
     समीक्षाओं
    -0.56
    StackNavigator
    -0.54
    tvguidetime
    -0.54
    Vidi
    -0.54
    POSITIVE LOGITS
    BeginContext
    0.53
    calipsis
    0.52
    出版年
    0.51
    xodo
    0.49
    ]")]
    0.49
    "](
    0.48
    unhofer
    0.45
    Gizmos
    0.44
     ResponseEntity
    0.43
     $
    0.43
    Activations Density 11.272%

    No Known Activations