© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 491
    Prev
    Next
    INDEX
    Explanations

    proper nouns, references to sources, and journalistic language.

    oai_token-act-pair · gemini-2.0-flash

    AP

    np_max-act · 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
     ProtoMessage
    -0.63
    ]]
    -0.59
    ArgsConstructor
    -0.57
    __*/
    -0.54
     word
    -0.53
    WireFormatLite
    -0.53
    mbals
    -0.52
     REPORTER
    -0.52
     ]];
    -0.51
    DataSnapshot
    -0.51
    POSITIVE LOGITS
     Houſe
    0.79
     itſelf
    0.79
     themſelves
    0.73
     myſelf
    0.71
     poffible
    0.71
     Reſ
    0.69
     pleaſure
    0.68
     houſe
    0.66
     Anſ
    0.65
     ſtate
    0.63
    Activations Density 0.753%

    No Known Activations