© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11996
    Prev
    Next
    INDEX
    Explanations

    code snippets that use dictionaries and the word "dict"

    oai_token-act-pair · gemini-2.0-flash

    dict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    dict
    -2.39
     dict
    -2.11
    Dict
    -1.77
     Dict
    -1.44
    DICT
    -1.27
    dicts
    -1.22
    Dictionary
    -1.09
     dic
    -1.09
     dictionary
    -1.09
    diction
    -1.06
    POSITIVE LOGITS
    AndEndTag
    0.63
     ModelExpression
    0.58
     ExecuteAsync
    0.57
     indépendant
    0.54
    inose
    0.54
     titulaire
    0.54
     conosco
    0.54
    ześnie
    0.53
    InputTagHelper
    0.52
     Chwiliwch
    0.52
    Activations Density 0.557%

    No Known Activations