© 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. 4753
    Prev
    Next
    INDEX
    Explanations

    code snippets or technical discussions about locks and security

    oai_token-act-pair · gemini-2.0-flash

    lock

    np_max-act-logits · gemini-2.0-flash

    lock

    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
     lock
    -2.58
     Lock
    -2.42
     LOCK
    -2.38
    lock
    -2.34
     locks
    -2.31
    Lock
    -2.30
     locking
    -2.30
     locked
    -2.27
    LOCK
    -2.17
     Locking
    -2.17
    POSITIVE LOGITS
     awakeFromNib
    0.52
    adpleegd
    0.46
    ミナル
    0.45
    :+:
    0.45
    îtra
    0.44
    contentLoaded
    0.43
     đạo
    0.43
    Pyx
    0.42
     државе
    0.41
    rade
    0.41
    Activations Density 0.599%

    No Known Activations