© 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. 12099
    Prev
    Next
    INDEX
    Explanations

    racial or group identifiers used in a negative or segregating way.

    oai_token-act-pair · gemini-2.0-flash

    Black

    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
     tartalomajánló
    -0.65
    Dữ
    -0.65
    Sucesor
    -0.64
     gynhyrchwyd
    -0.64
    <bos>
    -0.63
    ########.
    -0.62
    __":
    -0.59
    adpleegd
    -0.58
    }]
    -0.57
     كومونز
    -0.57
    POSITIVE LOGITS
    StoryboardSegue
    0.56
     kimse
    0.52
     autrefois
    0.47
    memoized
    0.47
    MLLoader
    0.47
    UnitTesting
    0.46
    .
    0.44
    ArgumentParser
    0.44
    SuccessListener
    0.43
    vertx
    0.43
    Activations Density 2.831%

    No Known Activations