© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3072
    Prev
    Next
    INDEX
    Explanations

    contextual words related to actions or things one can "try" to do in order to affect an outcome.

    oai_token-act-pair · gemini-2.0-flash

    conjunctions/prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     attempts
    -0.56
     attempt
    -0.54
     försö
    -0.53
     Attempt
    -0.52
    Attempts
    -0.51
    attempt
    -0.50
     proberen
    -0.49
    IsContent
    -0.49
     trying
    -0.49
     Attempts
    -0.49
    POSITIVE LOGITS
    下载附件
    0.70
     typelib
    0.67
    IonicModule
    0.59
     insuffisamment
    0.59
    AndroidJUnit
    0.59
    WebVitals
    0.57
    日閲覧
    0.57
    Pautan
    0.57
    ConstraintMaker
    0.56
    Personensuche
    0.55
    Activations Density 42.607%

    No Known Activations