© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7460
    Prev
    Next
    INDEX
    Explanations

    proper nouns and dates while also identifying the beginning of a sentence

    oai_token-act-pair · gemini-2.0-flash

    organized events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    oredCriteria
    -0.66
    Sucesor
    -0.57
    المناصب
    -0.56
     <=",
    -0.54
     jsPsych
    -0.54
     continued
    -0.53
    SharedCtor
    -0.50
    Coro
    -0.50
    toBeTruthy
    -0.48
     tower
    -0.48
    POSITIVE LOGITS
     виправивши
    0.62
    出版年
    0.59
    HomeAsUpEnabled
    0.58
    φα
    0.56
    󠁢
    0.52
     pavillon
    0.51
     consacré
    0.50
    iettes
    0.49
    figer
    0.49
     connaissent
    0.48
    Activations Density 4.394%

    No Known Activations