© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12100
    Prev
    Next
    INDEX
    Explanations

    the words "been," "was," "has," often followed by another verb

    oai_token-act-pair · gemini-2.0-flash

    been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     been
    -0.54
    Становништво
    -0.49
    曖昧さ回避
    -0.48
    theoremstyle
    -0.46
    Népesség
    -0.45
     Rumuni
    -0.43
    <bos>
    -0.42
     beve
    -0.42
    стоя
    -0.41
     בני
    -0.41
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.67
    Obrázky
    0.63
    orianCalendar
    0.58
     LUMP
    0.58
    "](
    0.57
    AddHtmlAttribute
    0.57
    leaner
    0.57
    setViewportView
    0.56
    ISupport
    0.55
    ürlich
    0.54
    Activations Density 2.572%

    No Known Activations