© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2146
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "to [verb]" or "[verb] to".

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    yorsunuz
    -0.65
     milliers
    -0.61
     défauts
    -0.59
     dizaines
    -0.58
     centaines
    -0.57
    wo
    -0.57
     campeão
    -0.54
     agujeros
    -0.53
     Logs
    -0.53
     defectos
    -0.51
    POSITIVE LOGITS
    RTLD
    0.73
    InstanceState
    0.73
     AssemblyCulture
    0.60
     AttributeSet
    0.57
    VersionUID
    0.57
     StatefulWidget
    0.56
    ConstraintMaker
    0.56
    Hentet
    0.54
    gnore
    0.54
    henswürdigkeiten
    0.53
    Activations Density 0.661%

    No Known Activations