© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6694
    Prev
    Next
    INDEX
    Explanations

    words related to coding or programming in Javascript, likely in Spanish

    oai_token-act-pair · gemini-2.0-flash

    es

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     es
    -0.90
     esp
    -0.59
    ]).
    -0.59
     ComVisible
    -0.58
    xFFFFFFFF
    -0.57
    mones
    -0.57
    ]]);
    -0.57
     Anson
    -0.57
    "]);
    -0.56
    ,:);
    -0.56
    POSITIVE LOGITS
     ſta
    0.64
    UnknownFieldSet
    0.63
     BoxFit
    0.61
     Efq
    0.61
     Majefty
    0.60
    出版年
    0.59
     Diſ
    0.59
    ILayout
    0.58
    AnchorStyles
    0.57
     Houſe
    0.56
    Activations Density 0.118%

    No Known Activations