© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13090
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs being used in a sentence

    oai_token-act-pair · gemini-2.0-flash

    "same"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    expandindo
    -0.85
     صوتيه
    -0.75
     esternos
    -0.74
    uxxxx
    -0.71
    HtmlAttribute
    -0.71
     مرئيه
    -0.70
    Rohy
    -0.66
    StreetMap
    -0.66
     مشين
    -0.65
    Autoritní
    -0.63
    POSITIVE LOGITS
     same
    2.77
    Same
    2.69
    same
    2.64
     Same
    2.55
     mesma
    2.17
    SAME
    2.17
     dezelfde
    2.17
     samma
    2.16
     hetzelfde
    2.14
     samme
    2.13
    Activations Density 5.274%

    No Known Activations