© 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. 7741
    Prev
    Next
    INDEX
    Explanations

    non-alphanumeric characters that often end sentences, especially question marks and periods

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign languages

    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
    lo
    -0.49
    .
    -0.44
    je
    -0.40
    +')
    -0.39
    ja
    -0.36
    mis
    -0.36
    /')
    -0.33
    }}
    -0.33
    Lo
    -0.33
    ju
    -0.33
    POSITIVE LOGITS
    +#+#
    1.09
    aarrggbb
    1.05
     Signalez
    1.02
     विश्वसनीयता
    1.01
    titleMargin
    1.01
     EconPapers
    0.99
    bibfield
    0.99
     AssemblyCulture
    0.97
    ThroughAttribute
    0.97
     للمعارف
    0.96
    Activations Density 0.450%

    No Known Activations