© 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. 8730
    Prev
    Next
    INDEX
    Explanations

    words starting with the "ph" sound

    oai_token-act-pair · gemini-2.0-flash

    ph

    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
     surla
    -0.67
    ThroughAttribute
    -0.66
    StoryboardSegue
    -0.60
     للاسماء
    -0.60
    rawDesc
    -0.51
    RectangleBorder
    -0.48
     فريبيس
    -0.48
     препратки
    -0.47
    +#+#
    -0.43
    ————————————
    -0.43
    POSITIVE LOGITS
     tố
    0.56
    ingeki
    0.56
    udine
    0.56
    aryen
    0.56
    tivis
    0.56
    thisis
    0.56
    EndContext
    0.55
    ilanth
    0.54
     Pons
    0.54
    etzung
    0.54
    Activations Density 8.574%

    No Known Activations