© 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. 3937
    Prev
    Next
    INDEX
    Explanations

    negative words and phrases related to political or religious groups

    oai_token-act-pair · gemini-2.0-flash

    terms related to force and imposition

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

    forced, imposed

    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
    EndProject
    -0.52
     Schwä
    -0.52
    ;->
    -0.51
     teneur
    -0.50
     Anzeige
    -0.47
    haustible
    -0.46
     accueillir
    -0.45
     manquer
    -0.44
     spéciaux
    -0.43
    حياته
    -0.43
    POSITIVE LOGITS
     forced
    1.51
     imposed
    1.49
     imposition
    1.43
     impose
    1.33
     forcing
    1.30
    forced
    1.26
     Forced
    1.26
    Forced
    1.24
     imposes
    1.19
     force
    1.18
    Activations Density 2.258%

    No Known Activations