© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14010
    Prev
    Next
    INDEX
    Explanations

    strings of digits and letters like measurements, dates, and alphanumeric strings

    oai_token-act-pair · gemini-2.0-flash

    references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    __(/*!
    -0.50
    szönöm
    -0.49
     cost
    -0.45
    fu
    -0.45
    裝
    -0.44
    tagext
    -0.44
     MatDialog
    -0.44
     Cost
    -0.43
    IsContent
    -0.43
    walde
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.88
     Roskov
    0.81
    IntoConstraints
    0.78
     INTERESAR
    0.75
     ویکی‌پدی
    0.74
     Wikimedijinoj
    0.73
    انيف
    0.70
    AsUp
    0.69
     AspNetCore
    0.69
    AndEndTag
    0.69
    Activations Density 23.755%

    No Known Activations