© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11854
    Prev
    Next
    INDEX
    Explanations

    spanish language technical programming documentation

    oai_token-act-pair · gemini-2.0-flash

    ▁el

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     évident
    -0.37
    (&_
    -0.37
     MainAxisSize
    -0.36
     immobilier
    -0.33
     abandonné
    -0.33
    CORBA
    -0.32
     conservé
    -0.32
    degenerate
    -0.31
    RemoveField
    -0.31
    icznie
    -0.31
    POSITIVE LOGITS
     myſelf
    1.14
     Theſe
    1.09
     himſelf
    1.04
     Efq
    1.02
     Anſ
    0.95
     itſelf
    0.94
     themſelves
    0.93
     whoſe
    0.92
     ſeveral
    0.92
     becauſe
    0.88
    Activations Density 0.361%

    No Known Activations