© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5606
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and quotation marks within political discussions, potentially along with numeric references

    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
     Majefty
    -0.85
     myſelf
    -0.85
     Efq
    -0.83
     يتيمه
    -0.83
     faſt
    -0.81
    ſelf
    -0.81
     becauſe
    -0.80
     itſelf
    -0.79
    aarrggbb
    -0.79
     الحره
    -0.79
    POSITIVE LOGITS
    States
    0.55
     States
    0.55
     Risk
    0.48
    Class
    0.47
    State
    0.47
    円
    0.47
     Life
    0.46
     International
    0.46
    Reject
    0.45
    Reg
    0.44
    Activations Density 4.921%

    No Known Activations