© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6613
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be," often in the context of a question or statement about a state.

    oai_token-act-pair · gemini-2.0-flash

    be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    cshtml
    -0.69
    Hentet
    -0.69
    IsContent
    -0.67
    LayoutStyle
    -0.63
    _));
    -0.59
     disambiguazione
    -0.53
     مشين
    -0.52
    JspWriter
    -0.52
     tqdm
    -0.52
     "}";
    -0.52
    POSITIVE LOGITS
     participação
    0.57
     supérieures
    0.55
    Autoritní
    0.54
     ContentValues
    0.54
    exitRule
    0.54
     partecipazione
    0.53
     importância
    0.51
     nélk
    0.51
    Referències
    0.49
     pelaksanaan
    0.47
    Activations Density 2.728%

    No Known Activations