© 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. 13948
    Prev
    Next
    INDEX
    Explanations

    the beginning of the word "Serb" or "Sermon" or similar sounding beginnings.

    oai_token-act-pair · gemini-2.0-flash

    Ser

    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
    PerformLayout
    -0.93
    ValueStyle
    -0.92
    +#+#
    -0.89
     ſtate
    -0.85
     AssemblyCulture
    -0.85
    Personensuche
    -0.83
     preſent
    -0.81
     pleaſure
    -0.81
     fubject
    -0.79
    Diweddarwch
    -0.79
    POSITIVE LOGITS
    فع
    0.40
    nehmen
    0.39
    arev
    0.37
     all
    0.37
    ier
    0.34
    fören
    0.34
    dingen
    0.34
    imir
    0.33
    onimo
    0.33
     keselamatan
    0.33
    Activations Density 0.550%

    No Known Activations