© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7179
    Prev
    Next
    INDEX
    Explanations

    sentences using non-English grammar structures with many subordinate clauses

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     I
    -2.36
    I
    -1.14
     tôi
    -0.85
     мені
    -0.82
    我
    -0.79
     я
    -0.79
    ฉัน
    -0.78
     मुझे
    -0.71
    所以我
    -0.71
     мне
    -0.69
    POSITIVE LOGITS
    ConstraintMaker
    0.58
    AxisAlignment
    0.55
    FieldBuilder
    0.54
    괄
    0.52
    TextSpan
    0.52
     gospod
    0.51
     OMIT
    0.50
    Ik
    0.50
     IndexPath
    0.49
    éndole
    0.49
    Activations Density 1.390%

    No Known Activations