© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4726
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or medical situations in which people have no more time to take action to solve their problem

    oai_token-act-pair · gemini-2.0-flash

    Variations of "any"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    MigrationBuilder
    -0.68
    findpost
    -0.66
    Lähteet
    -0.66
    !*\
    -0.65
    ControllerTest
    -0.63
    jmniej
    -0.63
     CoreData
    -0.62
    endphp
    -0.60
     تكبرها
    -0.60
    })));
    -0.60
    POSITIVE LOGITS
     any
    2.64
     anyone
    2.52
     anything
    2.42
    Any
    2.38
     Any
    2.33
     anybody
    2.33
    any
    2.31
    Anything
    2.22
     Anything
    2.19
    anything
    2.19
    Activations Density 6.948%

    No Known Activations