© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5964
    Prev
    Next
    INDEX
    Explanations

    titles of people, legal references, and musical references

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

    np_max-act-logits · 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
     espirituales
    -0.70
     judiciaire
    -0.68
     mensuales
    -0.67
     médié
    -0.66
     thermique
    -0.65
     chré
    -0.65
     littéraire
    -0.65
     supérieurs
    -0.65
     polaire
    -0.65
     économies
    -0.64
    POSITIVE LOGITS
    But
    0.94
    It
    0.93
    If
    0.90
    And
    0.85
    She
    0.84
    Its
    0.83
    They
    0.82
    You
    0.80
    He
    0.79
    There
    0.77
    Activations Density 3.339%

    No Known Activations