© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 84
    Prev
    Next
    INDEX
    Explanations

    subjective language and opinion

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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>
    -0.57
     الحره
    -0.56
    ñora
    -0.55
    tigem
    -0.55
    <?
    -0.54
    SBATCH
    -0.52
    CURLOPT
    -0.52
    ukone
    -0.50
     possibile
    -0.49
     kasarigan
    -0.48
    POSITIVE LOGITS
    帖最后由
    0.61
    اریخ
    0.60
    ArgsConstructor
    0.58
    marshaller
    0.55
    λία
    0.54
    kadot
    0.53
    istoitu
    0.52
    gegangen
    0.50
     those
    0.49
     Vikipedi
    0.49
    Activations Density 1.441%

    No Known Activations