© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 9921
    Prev
    Next
    INDEX
    Explanations

    the prefix "cru" or "nu" within a word

    oai_token-act-pair · gemini-2.0-flash

    cru

    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
    AddTagHelper
    -0.91
    onViewCreated
    -0.74
    ValueStyle
    -0.73
    antMatchers
    -0.69
    AndEndTag
    -0.66
    GIVEREF
    -0.65
    DoubleQuotes
    -0.65
    NegativeButton
    -0.63
    OGND
    -0.61
     AUSSI
    -0.61
    POSITIVE LOGITS
    μφωνα
    0.46
     Höhe
    0.43
     contrário
    0.41
     largo
    0.40
    ípio
    0.40
    מבר
    0.40
     acestea
    0.39
    dição
    0.39
    iseite
    0.38
     gramos
    0.38
    Activations Density 0.503%

    No Known Activations