© 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. 9305
    Prev
    Next
    INDEX
    Explanations

    the word "at" followed by other words

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "at" or related timing expressions

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

    at

    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
     Мексичка
    -0.71
    rungsseite
    -0.69
     Roskov
    -0.64
    ThroughAttribute
    -0.61
    Xna
    -0.59
    ंदीखरीदारी
    -0.56
    sider
    -0.53
    Jegyzetek
    -0.53
    DockStyle
    -0.53
     GenerationType
    -0.52
    POSITIVE LOGITS
     once
    3.38
    once
    2.94
    Once
    2.80
     Once
    2.78
     ONCE
    2.48
    ONCE
    2.27
     einmal
    1.59
     sekali
    1.58
    一旦
    1.46
    一度
    1.27
    Activations Density 1.236%

    No Known Activations