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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1352
    Prev
    Next
    INDEX
    Explanations

    text from restaurant reviews.

    oai_token-act-pair · gemini-2.0-flash

    restaurant/establishment reviews

    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
     review
    -2.58
     Review
    -2.44
    review
    -2.39
    Review
    -2.36
     reviews
    -2.33
     reviewed
    -2.31
     reviewing
    -2.27
     REVIEW
    -2.27
    REVIEW
    -2.11
     Reviews
    -2.09
    POSITIVE LOGITS
     astore
    0.57
    AddTagHelper
    0.55
    BagLayout
    0.53
    Rhestr
    0.47
    qrst
    0.46
    czo
    0.45
    maxcdn
    0.43
    antiation
    0.42
    ']))
    0.42
    awaiter
    0.42
    Activations Density 1.924%

    No Known Activations