© 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. 12662
    Prev
    Next
    INDEX
    Explanations

    sections of code

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
    i
    -0.45
     r
    -0.39
     i
    -0.37
    x
    -0.36
     p
    -0.35
     h
    -0.35
    p
    -0.33
     x
    -0.33
     m
    -0.33
     ik
    -0.32
    POSITIVE LOGITS
    ſelf
    1.39
     Majefty
    1.38
     Efq
    1.36
    ſelves
    1.33
     Houſe
    1.31
    neſs
    1.26
     Monfieur
    1.25
     myſelf
    1.24
     Jefus
    1.23
     houſe
    1.23
    Activations Density 11.909%

    No Known Activations