© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1856
    Prev
    Next
    INDEX
    Explanations

    phrases that describe conditional relationships or things that should not be.

    oai_token-act-pair · gemini-2.0-flash

    wh-words, that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ImageContext
    -0.67
    RDONLY
    -0.57
    AndEndTag
    -0.57
    Portail
    -0.56
    Portale
    -0.54
    stdc
    -0.54
    TargetException
    -0.54
     Normdatei
    -0.54
    TagMode
    -0.52
    ContentAsync
    -0.52
    POSITIVE LOGITS
    tvguidetime
    0.55
    例句
    0.54
     otherwise
    0.50
    󠁢
    0.50
    enumi
    0.50
     previously
    0.49
    navigationItem
    0.48
    previously
    0.46
    paksa
    0.46
     Coulson
    0.45
    Activations Density 2.461%

    No Known Activations