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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11922
    Prev
    Next
    INDEX
    Explanations

    capitalized words after helper words

    oai_token-act-pair · gemini-2.0-flash

    prepositions

    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
    <bos>
    -0.69
    ledem
    -0.44
    MessageInfo
    -0.43
    †
    -0.40
    انگلیسی
    -0.39
     tule
    -0.38
    قایناق‌لار
    -0.38
    NELL
    -0.38
    stoppable
    -0.38
    casts
    -0.38
    POSITIVE LOGITS
    TargetException
    0.61
     дописавши
    0.61
     >=",
    0.59
     متعلقه
    0.59
    SpringBootTest
    0.59
    httphttps
    0.57
    #+#
    0.57
    
    0.55
    endpush
    0.54
    luia
    0.54
    Activations Density 0.554%

    No Known Activations