© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10055
    Prev
    Next
    INDEX
    Explanations

    partial Russian words with emphasis on helping or repeating

    oai_token-act-pair · gemini-2.0-flash

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    InputBorder
    -0.57
    fjspx
    -0.56
     BoxFit
    -0.56
    providedIn
    -0.51
    rungsseite
    -0.51
     BoxDecoration
    -0.50
    .[/
    -0.50
    openConnection
    -0.49
    uffff
    -0.49
    giène
    -0.49
    POSITIVE LOGITS
     defStyleAttr
    0.60
    لكتر
    0.57
    łucha
    0.54
    انتهای
    0.53
    zegor
    0.53
     komende
    0.52
    spraak
    0.51
    íslu
    0.51
    ArgumentParser
    0.51
     lifted
    0.51
    Activations Density 0.200%

    No Known Activations