© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15823
    Prev
    Next
    INDEX
    Explanations

    text discussing a specific educational campus and its history

    oai_token-act-pair · gemini-2.0-flash

    Universities and colleges

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    +#+
    -0.63
     OMITBAD
    -0.58
    
    -0.57
     JpaRepository
    -0.53
    FieldDescriptor
    -0.53
    AutoresizingMask
    -0.50
    Vidite
    -0.49
    GEBURTSDATUM
    -0.49
     protoimpl
    -0.48
    JsonPropertyName
    -0.48
    POSITIVE LOGITS
    __':
    0.61
    StoreMessageInfo
    0.54
     })}
    0.52
    __':
    0.51
    kwij
    0.50
    JsonInclude
    0.49
     persistently
    0.46
    ształ
    0.46
     مخطط
    0.46
    AddTagHelper
    0.46
    Activations Density 0.993%

    No Known Activations