© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3094
    Prev
    Next
    INDEX
    Explanations

    the word "terminus" or a misspelling of it with related abbreviations

    oai_token-act-pair · gemini-2.0-flash

    US

    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
    ఔ
    -0.53
    SequentialGroup
    -0.52
    ilova
    -0.49
     estekak
    -0.48
     Lightboxes
    -0.46
    elemField
    -0.46
    styleType
    -0.46
    CGRectMake
    -0.46
     intptr
    -0.46
     Baillargeon
    -0.46
    POSITIVE LOGITS
    US
    2.05
    us
    2.03
     us
    1.90
     Us
    1.65
    Us
    1.63
     US
    1.62
    usa
    1.50
    uses
    1.44
    uso
    1.33
    uss
    1.31
    Activations Density 2.954%

    No Known Activations