© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7899
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to biological classification, especially of living things

    oai_token-act-pair · gemini-2.0-flash

    references to scientific or academic topics

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

    botany articles

    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
    AddTagHelper
    -0.75
    ]='\
    -0.68
     }}"></
    -0.68
    醐
    -0.60
     SwitchCompat
    -0.58
     ReactDOM
    -0.58
    }))
    -0.58
     出版
    -0.56
     EconPapers
    -0.53
    didSet
    -0.52
    POSITIVE LOGITS
     milk
    0.56
    íncia
    0.56
     científicas
    0.54
    mybatisplus
    0.51
     مشين
    0.50
     Milk
    0.50
     الدولى
    0.49
    #+#
    0.49
     per
    0.49
    Clos
    0.49
    Activations Density 1.253%

    No Known Activations