© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3896
    Prev
    Next
    INDEX
    Explanations

    text about budgets, spending, and cuts.

    oai_token-act-pair · gemini-2.0-flash

    budget cuts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     nakalista
    -0.74
    脚注の使い方
    -0.71
    Personensuche
    -0.69
     Increases
    -0.67
     @"/
    -0.66
     sevilla
    -0.65
    increased
    -0.65
    UrlResolution
    -0.64
     Increase
    -0.63
    Increases
    -0.63
    POSITIVE LOGITS
     tiefe
    0.41
    PointerException
    0.39
     blade
    0.39
     quinto
    0.39
    blade
    0.39
     podí
    0.39
     deep
    0.38
     Blades
    0.38
    hatsu
    0.38
     beras
    0.38
    Activations Density 1.488%

    No Known Activations