© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12486
    Prev
    Next
    INDEX
    Explanations

    words ending in "ing" and words starting with "co", as well as words with negative connotations.

    oai_token-act-pair · gemini-2.0-flash

    the ending -ing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     تضيفلها
    -0.73
     protoimpl
    -0.69
    writeFieldEnd
    -0.66
    __':
    -0.66
     resourceCulture
    -0.66
    出版年
    -0.65
    verifyException
    -0.64
    EDEFAULT
    -0.64
    TypedDataSet
    -0.63
     дописавши
    -0.63
    POSITIVE LOGITS
     communicating
    0.64
     activating
    0.62
     protecting
    0.61
    expressing
    0.60
     agreeing
    0.60
     having
    0.60
     registering
    0.59
    applying
    0.59
    having
    0.59
     participating
    0.59
    Activations Density 8.558%

    No Known Activations