© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9709
    Prev
    Next
    INDEX
    Explanations

    text containing family relationships and familial conflict.

    oai_token-act-pair · gemini-2.0-flash

    parent-child relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     otomatig
    -0.66
     endforeach
    -0.52
    StandardCharsets
    -0.49
    endforeach
    -0.47
     terminé
    -0.47
    ikit
    -0.47
    toThrow
    -0.46
     lenker
    -0.46
    chées
    -0.46
    نه
    -0.45
    POSITIVE LOGITS
    DockStyle
    0.69
     parental
    0.58
    PerformLayout
    0.57
    ifrance
    0.55
    GIVEREF
    0.55
    KURZBESCHREIBUNG
    0.54
     وصلة
    0.53
    SizeF
    0.52
     dál
    0.52
    parental
    0.52
    Activations Density 0.269%

    No Known Activations