Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14461
    Prev
    Next
    INDEX
    Explanations

    snippets of Portuguese code

    oai_token-act-pair · gemini-2.0-flash

    Portuguese programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    KommentareTeilen
    -0.94
    tagHelperRunner
    -0.93
    Datuak
    -0.82
    ArgsConstructor
    -0.80
    ########.
    -0.78
    MLLoader
    -0.77
    istoitu
    -0.74
     CURIAM
    -0.70
    Personendaten
    -0.70
    횟
    -0.70
    POSITIVE LOGITS
     o
    0.83
     a
    0.83
     die
    0.56
     os
    0.53
     as
    0.52
     az
    0.50
    %)$
    0.48
    ventory
    0.47
     pintu
    0.45
     собой
    0.43
    Activations Density 0.827%

    No Known Activations