© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 3139
    Prev
    Next
    INDEX
    Explanations

    the word "to" followed by a verb.

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ]_{\
    -0.60
    }));
    
    -0.57
    Geplaatst
    -0.57
    principalColumn
    -0.56
    )))));
    -0.56
    )];
    
    -0.55
    ulos
    -0.54
    }))
    
    -0.53
    }`);
    -0.53
    Personensuche
    -0.52
    POSITIVE LOGITS
     tie
    0.57
     cite
    0.56
     skip
    0.54
     fill
    0.54
     eat
    0.54
     isolate
    0.53
     prepare
    0.53
     tame
    0.52
     Tie
    0.51
    regate
    0.51
    Activations Density 1.507%

    No Known Activations