© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3637
    Prev
    Next
    INDEX
    Explanations

    high-value adjectives and nouns pertaining to quantitative results when discussing scientific studies

    oai_token-act-pair · gemini-2.0-flash

    high

    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
     marié
    -0.51
    avedra
    -0.50
     näm
    -0.48
     more
    -0.48
     ketiga
    -0.47
    何より
    -0.47
     chrétiens
    -0.47
     trasferimento
    -0.46
     âmes
    -0.46
     πιο
    -0.46
    POSITIVE LOGITS
    +#+#
    0.94
    AnchorStyles
    0.73
    ArgsConstructor
    0.72
     esternos
    0.69
    ConstraintMaker
    0.68
    SourceChecksum
    0.66
     ProtoMessage
    0.66
    UserScript
    0.65
    ContainerState
    0.65
    tagHelperRunner
    0.65
    Activations Density 9.463%

    No Known Activations