© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14883
    Prev
    Next
    INDEX
    Explanations

    descriptions of video game skills or abilities

    oai_token-act-pair · gemini-2.0-flash

    Anime

    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
     كومونز
    -0.77
     ویکی‌پدیای
    -0.63
    ---*/
    -0.60
     muualla
    -0.60
    NewUrlParser
    -0.57
     <<<<<<<<<<<<<<
    -0.55
    PreExecute
    -0.54
    ItemBackground
    -0.54
     linkovi
    -0.54
    ineno
    -0.52
    POSITIVE LOGITS
     Ichigo
    0.49
     suprême
    0.49
     kuni
    0.48
     Joshi
    0.48
     Sasaki
    0.47
     Natsu
    0.47
     Begründung
    0.46
     Rui
    0.45
     verbs
    0.45
     sakura
    0.45
    Activations Density 10.128%

    No Known Activations