© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1070
    Prev
    Next
    INDEX
    Explanations

    company names, addresses or citations in legal documents

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Inc
    -2.20
     Jr
    -2.06
    Inc
    -1.92
     inc
    -1.69
    inc
    -1.63
     INC
    -1.60
     LLC
    -1.52
     Sr
    -1.47
    Jr
    -1.46
     Ltd
    -1.41
    POSITIVE LOGITS
    ,
    0.63
    ]',
    0.42
    }',
    0.42
    '],
    0.42
     Darüber
    0.41
    walde
    0.41
     ['',
    0.40
    >",
    0.39
    }",
    0.38
    titutes
    0.38
    Activations Density 3.085%

    No Known Activations