© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9573
    Prev
    Next
    INDEX
    Explanations

    words that denote physical violence and the use of force.

    oai_token-act-pair · gemini-2.0-flash

    words associated with legal or contrasting actions

    np_token-act-pair-logits · gpt-4o-mini

    throwing/directing actions

    np_max-act-logits · gemini-2.0-flash
    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
     pinulongan
    -0.56
    ToSend
    -0.54
    ->___
    -0.51
     gyhoeddwyd
    -0.51
    Халык
    -0.50
     kaarangay
    -0.49
    Send
    -0.49
    dafx
    -0.48
     Send
    -0.47
    urp
    -0.47
    POSITIVE LOGITS
    EndInit
    0.62
     conto
    0.60
    Биография
    0.60
     READER
    0.59
     indisponible
    0.57
    ArgumentParser
    0.54
    Cuenta
    0.53
    ButtonStyle
    0.53
    RegressionTest
    0.53
     Cuenta
    0.51
    Activations Density 31.323%

    No Known Activations