Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1756
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of music

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.70
    providedIn
    -0.63
     CreateTagHelper
    -0.63
    __":
    -0.59
    SuccessListener
    -0.57
    Gön
    -0.56
     تضيفلها
    -0.56
    localctx
    -0.55
     viewDidLoad
    -0.54
     createState
    -0.54
    POSITIVE LOGITS
    UnknownFields
    0.59
    <bos>
    0.56
     referenties
    0.55
     pandémie
    0.52
    xtures
    0.50
    warted
    0.49
    ablon
    0.47
    BufferException
    0.47
     leggen
    0.47
     '/';
    0.46
    Activations Density 4.256%

    No Known Activations