© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6111
    Prev
    Next
    INDEX
    Explanations

    people

    oai_token-act-pair · gemini-2.0-flash

    developers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    AndEndTag
    -0.72
    memoized
    -0.60
    LLocation
    -0.58
     محفوظة
    -0.57
    TestingModule
    -0.56
    allowNull
    -0.54
     aapt
    -0.52
    springframework
    -0.52
    cassert
    -0.52
    .$,
    -0.51
    POSITIVE LOGITS
     Shakspeare
    0.67
     Monfieur
    0.66
     myſelf
    0.65
     Huguen
    0.65
     ſeveral
    0.64
     purpoſe
    0.64
     uſe
    0.64
     griega
    0.61
     Cæsar
    0.61
     Reſ
    0.61
    Activations Density 2.723%

    No Known Activations