© 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. 3989
    Prev
    Next
    INDEX
    Explanations

    code snippets containing words related to Javascript objects and properties

    oai_token-act-pair · gemini-2.0-flash

    Multilingual code/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
     her
    -2.84
    her
    -1.81
    Her
    -1.55
     hers
    -1.29
     Her
    -1.27
    她的
    -1.20
     HER
    -1.19
    彼女の
    -1.16
     herself
    -1.16
     ее
    -1.08
    POSITIVE LOGITS
    Ella
    0.65
     surla
    0.59
     okuyayım
    0.58
     NSCoder
    0.57
     Ella
    0.57
     للمعارف
    0.56
     cardíaca
    0.55
     feminina
    0.53
    quels
    0.52
    BufferException
    0.52
    Activations Density 0.893%

    No Known Activations