© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 5182
    Prev
    Next
    INDEX
    Explanations

    the word "pocket"

    oai_token-act-pair · gemini-2.0-flash

    pocket

    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
    <bos>
    -1.48
    ])));
    -0.79
    '));
    
    -0.79
    клопе
    -0.77
    "));
    
    -0.73
    ]."
    -0.72
    })));
    -0.71
     }}$
    -0.70
    /');
    -0.70
    ))));
    -0.69
    POSITIVE LOGITS
    telse
    0.69
    nocache
    0.64
     SqlCommand
    0.61
    ActivityCompat
    0.60
     Administr
    0.59
     quelcon
    0.59
     plomb
    0.58
     constitucional
    0.55
    yethylene
    0.54
     confund
    0.54
    Activations Density 1.557%

    No Known Activations