© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5329
    Prev
    Next
    INDEX
    Explanations

    text which represents formal mathematical exposition or long sentences involving family lineage

    oai_token-act-pair · gemini-2.0-flash

    confusion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     caoutchouc
    -0.54
     Exacts
    -0.50
    XMLSchema
    -0.46
    NullException
    -0.44
    nasel
    -0.40
    petito
    -0.39
    WritableDatabase
    -0.38
    +#+#
    -0.38
    boxylic
    -0.38
    $_['
    -0.38
    POSITIVE LOGITS
     Mix
    1.23
     mix
    1.22
     MIX
    1.18
     confusion
    1.15
     mixed
    1.15
     Mixing
    1.13
     mixes
    1.12
    mix
    1.10
    MIX
    1.09
     mixing
    1.09
    Activations Density 1.931%

    No Known Activations