© 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. 6172
    Prev
    Next
    INDEX
    Explanations

    references to Apple products in the context of privacy concerns.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or nouns

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

    Apple products

    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
    batore
    -0.61
     HasFactory
    -0.58
    headings
    -0.58
    .~(\
    -0.57
    AndEndTag
    -0.57
    WAUKEE
    -0.56
     للمعارف
    -0.56
    ----</
    -0.56
    ERMIN
    -0.55
     fermés
    -0.54
    POSITIVE LOGITS
    ########.
    0.68
    Clik
    0.54
    MENAFN
    0.53
    GraphicsUnit
    0.53
    AnimationsModule
    0.52
    بوابة
    0.47
    Buf
    0.45
    amp
    0.45
    es
    0.44
    jsonwebtoken
    0.44
    Activations Density 1.105%

    No Known Activations