© 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. 8797
    Prev
    Next
    INDEX
    Explanations

    hyphens and numbers

    oai_token-act-pair · 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
     Normdatei
    -0.55
    abestanden
    -0.54
    niająca
    -0.53
     NSCoder
    -0.52
    feof
    -0.51
     ſeveral
    -0.50
    FileInputStream
    -0.50
    timation
    -0.49
    etheless
    -0.48
    __':
    -0.47
    POSITIVE LOGITS
     فريبيس
    0.66
     onCreateView
    0.63
    PreferredItem
    0.53
    ണ്
    0.53
    AndroidJUnit
    0.53
    istos
    0.50
    rovnik
    0.48
     الدولى
    0.48
    ModelForm
    0.46
    ادث
    0.45
    Activations Density 0.420%

    No Known Activations