© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6666
    Prev
    Next
    INDEX
    Explanations

    the word "conscious", often preceded or followed by related words.

    oai_token-act-pair · gemini-2.0-flash

    conscious

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Reſ
    -0.75
     deſt
    -0.73
     poffe
    -0.73
     ſte
    -0.70
     Monfieur
    -0.70
     Diſ
    -0.68
     tranſ
    -0.67
     ſtand
    -0.66
    1
    -0.66
    <bos>
    -0.65
    POSITIVE LOGITS
    __":
    
    1.09
     EconPapers
    1.04
     utafitiHapana
    1.02
    )':
    0.99
    AnchorStyles
    0.94
    |')
    0.93
    >--}}
    0.93
    )];
    
    0.93
    ]));
    
    0.91
    IsMutable
    0.91
    Activations Density 0.652%

    No Known Activations