© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11050
    Prev
    Next
    INDEX
    Explanations

    the word "regular"

    oai_token-act-pair · gemini-2.0-flash

    regular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     препратки
    -0.74
     devriez
    -0.71
     nakalista
    -0.65
    الإنجليزية
    -0.63
     Depp
    -0.63
     regular
    -0.61
    onAttach
    -0.59
    Personensuche
    -0.59
    tät
    -0.59
     APPELLANT
    -0.58
    POSITIVE LOGITS
    ">\
    0.59
     appuntamento
    0.59
    entrale
    0.59
     verlassen
    0.57
    BACA
    0.57
    omation
    0.56
     happenings
    0.55
    resaid
    0.55
    sivité
    0.55
    venor
    0.54
    Activations Density 0.866%

    No Known Activations