© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11301
    Prev
    Next
    INDEX
    Explanations

    a mix of Malay and Mandarin words mixed in with English words

    oai_token-act-pair · gemini-2.0-flash

    word patterns in non-English languages

    np_token-act-pair-logits · gpt-4o-mini

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    BufferException
    -0.68
    buttonBar
    -0.66
    tableFuture
    -0.64
    fromnode
    -0.57
    ỡng
    -0.56
    sidemargin
    -0.55
     fallu
    -0.54
     Theſe
    -0.52
    Достоинства
    -0.51
    RetentionPolicy
    -0.50
    POSITIVE LOGITS
     affitto
    0.74
     épaules
    0.65
    ыгана
    0.63
    isfile
    0.59
    migrationBuilder
    0.59
    得
    0.58
    éndole
    0.56
     <",
    0.56
     fluent
    0.55
     influência
    0.55
    Activations Density 0.192%

    No Known Activations