© 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. 11454
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to companies, places, or trade names

    oai_token-act-pair · gemini-2.0-flash

    Offshore

    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
     
    -0.54
     */,
    -0.48
    <bos>
    -0.46
    </u>
    -0.45
    +#+
    -0.44
     PC
    -0.42
     very
    -0.42
    </strong>
    -0.41
    ClientSize
    -0.41
    ↵
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    1.10
     gynhyrchwyd
    1.03
     الدولى
    0.84
     فريبيس
    0.82
    Datuak
    0.82
    TestingModule
    0.82
    Hentet
    0.81
    ConstraintMaker
    0.76
    ValueStyle
    0.76
     يتيمه
    0.76
    Activations Density 1.080%

    No Known Activations