© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10611
    Prev
    Next
    INDEX
    Explanations

    non-English language, question-answer pairs, and the imperative/prohibitive mood

    oai_token-act-pair · gemini-2.0-flash

    period punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     en
    -0.53
     su
    -0.52
     le
    -0.52
     de
    -0.50
     der
    -0.49
     au
    -0.49
     se
    -0.48
     di
    -0.47
     la
    -0.46
     bu
    -0.46
    POSITIVE LOGITS
    ValueStyle
    0.88
     Roskov
    0.88
    Datuak
    0.85
     AssemblyCulture
    0.83
     InputDecoration
    0.82
     EconPapers
    0.81
    SequentialGroup
    0.80
    BeginContext
    0.79
    GEBURTSDATUM
    0.79
    IntoConstraints
    0.79
    Activations Density 2.332%

    No Known Activations