© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14114
    Prev
    Next
    INDEX
    Explanations

    court opinions discussing judiciary power, particularly words such as "court," "to," "the"

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Roskov
    -0.73
     $_"
    -0.70
    keeping
    -0.64
     $_(
    -0.63
    ThroughAttribute
    -0.63
     TextAppearance
    -0.61
    keeps
    -0.61
    graphies
    -0.60
     Efq
    -0.59
     Preven
    -0.59
    POSITIVE LOGITS
    ForRow
    0.59
    headed
    0.58
     FetchType
    0.57
    ModelForm
    0.49
    ImageContext
    0.49
     headed
    0.48
     forest
    0.48
     للمعارف
    0.47
    MO
    0.46
    BuilderFactory
    0.46
    Activations Density 3.383%

    No Known Activations