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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11366
    Prev
    Next
    INDEX
    Explanations

    phrases with words like "until", "before", or negative constructions describing something unknown in the past.

    oai_token-act-pair · gemini-2.0-flash

    recent events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.76
    WriteBarrier
    -0.63
    
    -0.59
     propOrder
    -0.54
     referrerpolicy
    -0.53
    Šaltiniai
    -0.53
    addPreferredGap
    -0.53
     насеље
    -0.52
     Wiktionnaire
    -0.51
    Kjelder
    -0.51
    POSITIVE LOGITS
    0.61
    
    0.57
    basicConfig
    0.54
     heretofore
    0.52
    IZABETH
    0.52
     đốc
    0.51
    DockStyle
    0.51
    Previously
    0.49
    цездатний
    0.49
    ]-->
    0.48
    Activations Density 1.002%

    No Known Activations