© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4585
    Prev
    Next
    INDEX
    Explanations

    verbs in the conditional or future tenses, conjugated with "je" or "tu"

    oai_token-act-pair · gemini-2.0-flash

    French text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    leqq
    -0.59
    ongono
    -0.56
     hatten
    -0.50
     been
    -0.48
    자인
    -0.46
     avevano
    -0.45
    까지
    -0.45
     собра
    -0.44
     habt
    -0.44
    appBar
    -0.44
    POSITIVE LOGITS
    would
    1.30
     would
    1.24
     WOULD
    1.23
    Would
    1.18
     Would
    1.16
     wouldnt
    0.76
     Wouldn
    0.74
    wouldn
    0.73
     tomorrow
    0.71
     snippetHide
    0.70
    Activations Density 0.668%

    No Known Activations