© 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. 3367
    Prev
    Next
    INDEX
    Explanations

    words expressing a state of being or the unnatural

    oai_token-act-pair · gemini-2.0-flash

    representing something

    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
    parsedMessage
    -0.71
    MigrationBuilder
    -0.65
     transfieras
    -0.55
    pfung
    -0.52
    queryInterface
    -0.51
    breos
    -0.50
    DebuggerNonUser
    -0.49
    któ
    -0.48
    rrggbb
    -0.48
     préc
    -0.47
    POSITIVE LOGITS
     embodied
    0.76
    ftagPool
    0.76
     reflected
    0.76
     echoed
    0.71
     represented
    0.71
     exemplified
    0.71
     manifested
    0.70
     expressed
    0.68
     underscored
    0.68
     apparent
    0.68
    Activations Density 3.721%

    No Known Activations