© 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. 6312
    Prev
    Next
    INDEX
    Explanations

    the phrase "state of the art"

    oai_token-act-pair · gemini-2.0-flash

    state of the art

    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
     فريبيس
    -1.09
    RenderAtEndOf
    -1.08
     Wiktionnaire
    -1.06
    Personensuche
    -1.00
     esternos
    -0.99
     Мексичка
    -0.96
     المعيارى
    -0.93
    endphp
    -0.92
    expandindo
    -0.92
    IUrlHelper
    -0.90
    POSITIVE LOGITS
     state
    0.65
    state
    0.56
     the
    0.53
     pol
    0.47
    pol
    0.46
     ch
    0.45
     estado
    0.42
     State
    0.41
    ac
    0.40
     poly
    0.40
    Activations Density 0.364%

    No Known Activations