© 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. 10547
    Prev
    Next
    INDEX
    Explanations

    strings from a code snippet that define categories for food

    oai_token-act-pair · gemini-2.0-flash

    food-related 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
     >=",
    -0.64
     виправивши
    -0.64
    yntaxException
    -0.61
    IndentedString
    -0.60
     مشين
    -0.60
    ỡng
    -0.54
    AutoScaleMode
    -0.52
    erapeutics
    -0.52
     OMITBAD
    -0.52
     ApiException
    -0.49
    POSITIVE LOGITS
     Trujillo
    0.54
     personali
    0.51
     Sanjay
    0.48
    Wort
    0.48
    CGContext
    0.48
     patched
    0.47
    zoll
    0.46
     produt
    0.46
     Diony
    0.46
     tubers
    0.46
    Activations Density 3.520%

    No Known Activations