© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3180
    Prev
    Next
    INDEX
    Explanations

    the German word "aus"

    oai_token-act-pair · gemini-2.0-flash

    the token "aus" with high frequency

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    adze
    -0.49
    ::_('
    -0.45
    Damit
    -0.45
     tachy
    -0.44
    intrag
    -0.42
    CloseHandle
    -0.41
    ohner
    -0.41
    toCharArray
    -0.41
    Ljava
    -0.41
    icali
    -0.40
    POSITIVE LOGITS
    исленность
    0.74
    SequentialGroup
    0.74
     '\\;'
    0.66
    ,:);
    0.66
    AxisAlignment
    0.65
     oprot
    0.63
    Erstellt
    0.63
    %</
    0.62
    الحياه
    0.61
    %");
    0.60
    Activations Density 0.333%

    No Known Activations