© 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. 8802
    Prev
    Next
    INDEX
    Explanations

    somewhat arbitrarily find capitalized abbreviations and names

    oai_token-act-pair · gemini-2.0-flash

    Bre

    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
    Ak
    -0.12
     intptr
    -0.11
     RoutedEventArgs
    -0.10
    AN
    -0.10
    
    -0.10
    /*
    -0.09
    OR
    -0.08
    IUrlHelper
    -0.08
     []:
    -0.08
    IMPORTED
    -0.07
    POSITIVE LOGITS
    verständlich
    0.73
    helf
    0.70
    potamus
    0.69
    crackers
    0.68
    ctum
    0.68
    ETHING
    0.68
    ")));
    0.68
    ozat
    0.68
    pike
    0.68
    hells
    0.67
    Activations Density 21.024%

    No Known Activations