© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12357
    Prev
    Next
    INDEX
    Explanations

    verbs that have 'ing' after the base of the word

    oai_token-act-pair · gemini-2.0-flash

    Code/descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ing
    -2.23
    ING
    -1.84
    ting
    -1.50
    ging
    -1.34
    TING
    -1.26
    ning
    -1.23
    bing
    -1.17
    izing
    -1.07
    ingi
    -1.06
    ding
    -1.05
    POSITIVE LOGITS
    XmlAccessType
    0.42
     charging
    0.39
    genheit
    0.38
    picasso
    0.38
    alat
    0.37
    WithEmail
    0.36
    makeText
    0.35
    kalan
    0.35
    PostBack
    0.35
    ellites
    0.34
    Activations Density 2.131%

    No Known Activations