© 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. 14684
    Prev
    Next
    INDEX
    Explanations

    positive predictive values in medical studies, and also C code

    oai_token-act-pair · gemini-2.0-flash

    say "V" words

    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
     v
    -1.49
    v
    -1.27
    ｖ
    -0.85
    vi
    -0.84
    vs
    -0.78
     vi
    -0.77
    vv
    -0.76
    ve
    -0.75
    vus
    -0.74
     ve
    -0.74
    POSITIVE LOGITS
     V
    0.59
    V
    0.54
     مشين
    0.53
     Վ
    0.52
    {~
    0.50
     Ви
    0.48
     Viagra
    0.47
     mắn
    0.46
    PerformLayout
    0.46
     فريبيس
    0.45
    Activations Density 2.226%

    No Known Activations