© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9912
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "help" and words that have similar meaning such as seeing and improving.

    oai_token-act-pair · gemini-2.0-flash

    assistance and observation verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     vertes
    -0.49
    melho
    -0.47
     Gegenteil
    -0.47
    QUALITY
    -0.45
     fotografico
    -0.43
     ouest
    -0.43
     platí
    -0.42
     judiciaire
    -0.42
    StringProperty
    -0.42
     are
    -0.41
    POSITIVE LOGITS
    تقاوى
    1.05
    énario
    0.94
    expandindo
    0.92
    脚注の使い方
    0.91
     שוליים
    0.90
     autorytatywna
    0.90
     intptr
    0.87
     propOrder
    0.85
    OGND
    0.82
    Diwedd
    0.81
    Activations Density 1.483%

    No Known Activations