© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13998
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to negative consequences or misfortune happening to people.

    oai_token-act-pair · gemini-2.0-flash

    Unfortunate situations

    np_max-act-logits · gemini-2.0-flash
    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
     pouvoit
    -0.64
     contemporaine
    -0.60
     étoient
    -0.57
    NameInMap
    -0.57
    المناصب
    -0.56
     användas
    -0.54
    +#+#
    -0.53
     avoient
    -0.53
     étoit
    -0.52
    ungere
    -0.49
    POSITIVE LOGITS
    });*/
    0.60
     with
    0.58
     wishing
    0.57
     EconPapers
    0.56
     sitting
    0.56
    >-->
    0.56
     questioning
    0.56
    AccessFile
    0.55
    ViewFeatures
    0.54
     ExecuteAsync
    0.54
    Activations Density 4.781%

    No Known Activations