© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12378
    Prev
    Next
    INDEX
    Explanations

    XML/HTML formatting tags and names of organizations

    oai_token-act-pair · gemini-2.0-flash

    NM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Portail
    -0.68
     تضيفلها
    -0.56
    writeFieldEnd
    -0.54
     Италијани
    -0.54
    writeField
    -0.54
    contentLoaded
    -0.53
    thâu
    -0.51
     уж
    -0.50
     mergeFrom
    -0.49
    Diweddarwch
    -0.48
    POSITIVE LOGITS
     SafeMath
    0.53
    CloseOperation
    0.52
    weisungen
    0.49
    ChildScrollView
    0.48
    adaptiveStyles
    0.46
     ObjectParameter
    0.46
     task
    0.46
    ("")]
    0.46
    PROTOBUF
    0.46
    getHours
    0.45
    Activations Density 2.800%

    No Known Activations