© 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. 5700
    Prev
    Next
    INDEX
    Explanations

    code snippets that initialize new objects

    oai_token-act-pair · gemini-2.0-flash

    instances of the token 'new'

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

    foreign words

    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
    ho
    -0.50
     hoarding
    -0.49
     crossorigin
    -0.46
     disclosures
    -0.45
     amarela
    -0.45
    落
    -0.45
     tartar
    -0.45
    div
    -0.44
    chließ
    -0.44
     paso
    -0.43
    POSITIVE LOGITS
     للاسماء
    1.07
     незавершена
    0.89
    SBATCH
    0.73
     beginnetje
    0.71
     يتيمه
    0.65
    RenderAtEndOf
    0.65
     ProtoMessage
    0.64
    Ծանոթ
    0.61
    تقاوى
    0.61
     الحره
    0.61
    Activations Density 0.166%

    No Known Activations