© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13324
    Prev
    Next
    INDEX
    Explanations

    the word "ultimate" and related words (e.g. age, deck, chimneys, track, optimum).

    oai_token-act-pair · gemini-2.0-flash

    ultimate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Optimal
    -0.85
    Optimal
    -0.77
    optimal
    -0.73
     optimal
    -0.72
     betweenstory
    -0.69
    ScopeManager
    -0.60
     egli
    -0.60
    sidemargin
    -0.57
    Компания
    -0.56
     optimum
    -0.54
    POSITIVE LOGITS
    viewDidLoad
    0.57
    ừa
    0.56
    textTheme
    0.56
    ̂
    0.56
    ạm
    0.56
    áss
    0.55
    essen
    0.54
    Ծանոթ
    0.53
    CAPTURE
    0.53
     tài
    0.52
    Activations Density 0.782%

    No Known Activations