© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4863
    Prev
    Next
    INDEX
    Explanations

    descriptions of product qualities, specifically for cosmetics or apparel

    oai_token-act-pair · gemini-2.0-flash

    descriptions

    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
    ngdoc
    -0.57
     विश्वसनीयता
    -0.56
     Normdatei
    -0.56
     العنوان
    -0.55
    SPATH
    -0.53
     AssemblyCompany
    -0.52
    GraphicsUnit
    -0.51
     BoxDecoration
    -0.50
     onData
    -0.50
    DoubleQuotes
    -0.49
    POSITIVE LOGITS
    tagHelperRunner
    0.69
    exitRule
    0.50
    expandindo
    0.49
    Portail
    0.48
    "}";
    0.47
    yntaxException
    0.46
    vik
    0.45
     Voss
    0.45
    AddWithValue
    0.44
     VIET
    0.44
    Activations Density 2.566%

    No Known Activations