© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10657
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs, especially "to be" and "not"

    oai_token-act-pair · gemini-2.0-flash

    forms of "to be"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Efq
    -0.88
    SourceChecksum
    -0.85
    )";
    -0.81
     Jefus
    -0.75
    CheckedChanged
    -0.75
    )");
    -0.74
    脚注の使い方
    -0.73
     HasFactory
    -0.73
    "]);
    -0.72
     Theſe
    -0.71
    POSITIVE LOGITS
    tagext
    0.38
     full
    0.37
     crescere
    0.36
     fermés
    0.35
    Full
    0.35
    Ursula
    0.35
     commerciali
    0.35
     Full
    0.33
     supuestamente
    0.33
     culturelles
    0.33
    Activations Density 1.123%

    No Known Activations