© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5403
    Prev
    Next
    INDEX
    Explanations

    phrases asserting difficulty or something being necessary

    oai_token-act-pair · gemini-2.0-flash

    the concept of necessity

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

    necessary

    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
     könnt
    -0.51
    Right
    -0.48
     could
    -0.48
     مُعرِّف
    -0.47
    Kind
    -0.47
    RIGHT
    -0.47
    right
    -0.46
     bỏ
    -0.45
     Tim
    -0.44
     Right
    -0.44
    POSITIVE LOGITS
     necessary
    1.64
    necessary
    1.48
     Necessary
    1.41
    Necessary
    1.26
     neceffary
    1.19
     NECESS
    1.13
     necesario
    0.99
     necessario
    0.94
     neces
    0.92
     nécessaire
    0.92
    Activations Density 1.082%

    No Known Activations