© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5376
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with opinions, perceptions, and observations

    oai_token-act-pair · gemini-2.0-flash

    see

    np_max-act-logits · gemini-2.0-flash

    see

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     kasarigan
    -0.49
     verrez
    -0.47
     Familienname
    -0.47
    ेश
    -0.46
    stdc
    -0.46
     تانيه
    -0.45
    󠁮
    -0.44
    NIS
    -0.44
    cuentes
    -0.43
     BPS
    -0.42
    POSITIVE LOGITS
     it
    0.77
     what
    0.73
     this
    0.70
     these
    0.64
     the
    0.63
    AccessorTable
    0.62
    MessageOf
    0.60
    riwal
    0.57
     where
    0.57
     that
    0.56
    Activations Density 16.147%

    No Known Activations