© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4197
    Prev
    Next
    INDEX
    Explanations

    contentiousness and disagreement expressed through changes

    oai_token-act-pair · gemini-2.0-flash

    suddenly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    ReusableCell
    -0.85
    MessageTagHelper
    -0.62
    DebuggerNonUser
    -0.57
     userManager
    -0.56
    ()))
    -0.54
    InputTagHelper
    -0.53
    ufu
    -0.53
    󠁮
    -0.53
     ProtoMessage
    -0.52
    __*/
    -0.51
    POSITIVE LOGITS
     suddenly
    2.41
     Suddenly
    2.33
    Suddenly
    2.22
    suddenly
    2.14
     sudden
    1.77
     plötzlich
    1.70
     soudain
    1.59
     вдруг
    1.44
     Sudden
    1.38
    Sudden
    1.38
    Activations Density 1.655%

    No Known Activations