© 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. 15455
    Prev
    Next
    INDEX
    Explanations

    terms related to medicine or legal situations

    oai_token-act-pair · gemini-2.0-flash

    Legal and scientific studies

    np_max-act · gemini-2.0-flash

    say "word endings" Method used: 2 — tokens are suffixes completing stems; explanation: say "word endings"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     itſelf
    -0.98
     ―――――
    -0.98
     Theſe
    -0.96
     themſelves
    -0.94
     Efq
    -0.86
     myſelf
    -0.85
     ――――
    -0.83
     bershka
    -0.82
     Forumite
    -0.81
     ―――
    -0.79
    POSITIVE LOGITS
    reactstrap
    0.91
    æus
    0.75
    tableFuture
    0.74
     cykel
    0.72
     ennemis
    0.69
     Juifs
    0.69
    cdnjs
    0.68
    .*")]
    0.67
    jsdelivr
    0.67
    anoke
    0.66
    Activations Density 21.373%

    No Known Activations