© 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. 11341
    Prev
    Next
    INDEX
    Explanations

    phrases expressing preference or that something is good enough

    oai_token-act-pair · gemini-2.0-flash

    Acceptability or combination

    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
    NotIn
    -0.53
    çi
    -0.52
     Travellers
    -0.50
    ESTIC
    -0.47
     demurrer
    -0.46
    Marseille
    -0.46
    domés
    -0.46
     Bintang
    -0.45
     Volta
    -0.44
    ylo
    -0.44
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.69
    RenderAtEndOf
    0.66
    SBATCH
    0.63
     كومونز
    0.62
    mybatisplus
    0.60
    Personendaten
    0.57
     مشين
    0.57
    ]")]
    0.56
     BoxDecoration
    0.56
     EconPapers
    0.56
    Activations Density 0.773%

    No Known Activations