© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 441
    Prev
    Next
    INDEX
    Explanations

    code that throws exceptions because of unsupported media types

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     createSlice
    -0.64
     “
    -0.59
     "
    -0.52
    <bos>
    -0.50
     [
    -0.49
     
    -0.49
    ViewChild
    -0.47
     on
    -0.46
    InputBorder
    -0.46
    Brainz
    -0.44
    POSITIVE LOGITS
     itſelf
    0.81
    DockStyle
    0.78
     Jefus
    0.77
    menea
    0.70
     myſelf
    0.68
    SharedCtor
    0.68
     uſed
    0.67
     ]
    0.65
     Theſe
    0.65
     Monfieur
    0.64
    Activations Density 1.182%

    No Known Activations