© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13847
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and numeric ids

    oai_token-act-pair · gemini-2.0-flash

    References

    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
    馃
    -0.59
     McLaughlin
    -0.57
    miştir
    -0.57
     ۲۰۱
    -0.56
     import
    -0.55
    inus
    -0.54
    aldi
    -0.54
    ers
    -0.53
    (";
    -0.53
    ガジン
    -0.52
    POSITIVE LOGITS
     سكانية
    0.72
    djangoproject
    0.71
    ]")]
    0.69
    VersionUID
    0.69
    rungsseite
    0.69
    SharedDtor
    0.66
     DBNull
    0.66
    ValueStyle
    0.63
    detectChanges
    0.61
     bezeichneter
    0.58
    Activations Density 0.704%

    No Known Activations