© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14561
    Prev
    Next
    INDEX
    Explanations

    the word "it" followed by a form of the verb "to be."

    oai_token-act-pair · gemini-2.0-flash

    It

    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
     كومونز
    -0.57
    amaño
    -0.54
    lankton
    -0.53
    iecie
    -0.52
    portál
    -0.48
    mergeFrom
    -0.47
    pore
    -0.46
     PropTypes
    -0.46
     Hsi
    -0.45
    RenderAtEndOf
    -0.45
    POSITIVE LOGITS
    ViewFeatures
    0.77
    enumi
    0.71
     is
    0.66
     متعلقه
    0.61
    Tikang
    0.60
    })$}
    0.59
     cherchés
    0.58
    enumii
    0.58
     >=",
    0.57
    seamnă
    0.57
    Activations Density 3.109%

    No Known Activations