© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12207
    Prev
    Next
    INDEX
    Explanations

    the word "there" in different contexts, as well as similar words related to existence or possibility

    oai_token-act-pair · gemini-2.0-flash

    modal verbs indicating future actions

    np_token-act-pair-logits · gpt-4o-mini

    there

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     crdi
    -0.82
    ChildScrollView
    -0.80
    theless
    -0.73
     InputDecoration
    -0.68
    zzleHttp
    -0.68
     BoxFit
    -0.66
     cdti
    -0.66
     tdci
    -0.64
    Спасылкі
    -0.63
    BufferException
    -0.63
    POSITIVE LOGITS
     will
    0.71
     shall
    0.64
    will
    0.52
    ill
    0.50
    shall
    0.47
    ll
    0.46
     future
    0.46
     the
    0.46
    Mod
    0.45
     should
    0.44
    Activations Density 0.253%

    No Known Activations