© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12168
    Prev
    Next
    INDEX
    Explanations

    HTML image tags

    oai_token-act-pair · gemini-2.0-flash

    img

    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
    Obrázky
    -0.67
     arşivlendi
    -0.65
    ::$_
    -0.57
    addContainerGap
    -0.57
    SetBool
    -0.56
    Kie
    -0.56
     pyplot
    -0.55
     Mojo
    -0.55
    roid
    -0.54
     jsPsych
    -0.54
    POSITIVE LOGITS
     lenker
    0.49
    Rüyada
    0.48
    Londres
    0.46
    WriteTagHelper
    0.45
     okrąg
    0.45
    effetto
    0.44
     lantai
    0.44
     léger
    0.43
     bajos
    0.43
    Egypte
    0.42
    Activations Density 0.476%

    No Known Activations