© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13305
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical attacks and violence

    oai_token-act-pair · gemini-2.0-flash

    Violence

    np_max-act-logits · gemini-2.0-flash

    irregular verbs and words of confrontation

    np_token-act-pair-logits · gpt-4o-mini
    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
    ValueStyle
    -0.82
    تقاوى
    -0.81
    Tembelea
    -0.79
     utafitiHapana
    -0.77
    IBOutlet
    -0.74
    richTextPanel
    -0.73
    LabelTagHelper
    -0.71
    NewUrlParser
    -0.70
     صوتيه
    -0.70
    numerusform
    -0.69
    POSITIVE LOGITS
     as
    0.47
     sol
    0.45
     vár
    0.43
     hadapan
    0.42
     mis
    0.41
    .__
    0.41
    ).__
    0.41
    reale
    0.38
    REB
    0.38
    ORIA
    0.37
    Activations Density 5.838%

    No Known Activations