© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10295
    Prev
    Next
    INDEX
    Explanations

    the word "of" and words that end with "thereof."

    oai_token-act-pair · gemini-2.0-flash

    thereof/of

    np_max-act · gemini-2.0-flash

    of

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Roskov
    -0.56
    ècie
    -0.49
    HtmlAttribute
    -0.49
     gekomen
    -0.48
    Obrázky
    -0.48
    Autoritní
    -0.46
    Datuak
    -0.46
    ValueStyle
    -0.44
    ondissement
    -0.44
    XDECREF
    -0.43
    POSITIVE LOGITS
     vouloir
    0.60
    PageRoute
    0.57
    خواندن
    0.57
    rmtree
    0.57
     such
    0.57
     MotionEvent
    0.55
     '*':
    0.55
     tasche
    0.54
    MergeFrom
    0.54
    twimg
    0.54
    Activations Density 0.800%

    No Known Activations