© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6360
    Prev
    Next
    INDEX
    Explanations

    varied words, some related to legal or technical language, others to fantasy narratives

    oai_token-act-pair · gemini-2.0-flash

    unknownFields

    np_max-act · gemini-2.0-flash

    unknownFields Method used: 1 — Reason: repeated ▁unknownFields in MAX_ACTIVATING_TOKENS — unknownFields

    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_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
    _
    -0.84
    ↵
    -0.77
    (
    -0.71
    -
    -0.70
    +
    -0.68
    /
    -0.66
     +
    -0.65
     (
    -0.61
    :
    -0.61
    −
    -0.58
    POSITIVE LOGITS
     itſelf
    1.45
     myſelf
    1.16
     doubtnut
    1.12
     Jefus
    1.12
     RSITY
    1.12
    VERTISEMENT
    1.10
    VIRONMENT
    1.07
     $_"
    1.06
     himſelf
    1.06
    ſelf
    1.06
    Activations Density 17.419%

    No Known Activations