© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1129
    Prev
    Next
    INDEX
    Explanations

    something of a grab bag, including the substring 'ormal', words relating to quantum physics, and words that apply to comparisons such as 'different' and 'each'

    oai_token-act-pair · gemini-2.0-flash

    say the ending -tion

    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
     Promotions
    -0.85
     Reformation
    -0.79
    Promotions
    -0.77
     tions
    -0.77
    ConstraintMaker
    -0.77
    Revision
    -0.76
     Revisions
    -0.76
     Accommodations
    -0.76
     Nominations
    -0.76
    onAttach
    -0.75
    POSITIVE LOGITS
    Foo
    0.51
     QtCore
    0.50
    ImageContext
    0.48
    twimg
    0.47
    hadap
    0.47
     Stateful
    0.47
     trás
    0.46
     Bucks
    0.46
    CDS
    0.45
    rande
    0.45
    Activations Density 5.399%

    No Known Activations