© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8647
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific studies of soil

    oai_token-act-pair · gemini-2.0-flash

    soil

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     للاسماء
    -0.92
     متعلقه
    -0.88
     <=",
    -0.85
     Roskov
    -0.85
    expandindo
    -0.84
     otomatig
    -0.82
    KURZBESCHREIBUNG
    -0.82
    AndEndTag
    -0.82
     <>",
    -0.80
    tvguidetime
    -0.76
    POSITIVE LOGITS
    nisch
    0.47
    antd
    0.46
     ملا
    0.43
     لب
    0.43
     Lim
    0.43
    gy
    0.42
    한
    0.41
    anka
    0.41
     cỏ
    0.40
    näm
    0.40
    Activations Density 2.916%

    No Known Activations