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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11296
    Prev
    Next
    INDEX
    Explanations

    commas, periods, and the word "and" in varied contexts

    oai_token-act-pair · gemini-2.0-flash

    grammatical complexity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     InputDecoration
    -0.52
    AutoScaleMode
    -0.50
    "),
    -0.49
    oman
    -0.48
    ленно
    -0.47
    }?>
    -0.47
    `,`
    -0.46
    }};
    -0.46
    });*/
    -0.46
    ']='
    -0.45
    POSITIVE LOGITS
    findpost
    0.79
    msgSender
    0.61
    SBATCH
    0.59
    ⓧ
    0.59
     défin
    0.54
    AutoField
    0.52
     hjär
    0.50
    MLLoader
    0.49
    OrBuilder
    0.49
    ImageContext
    0.47
    Activations Density 1.662%

    No Known Activations