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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10561
    Prev
    Next
    INDEX
    Explanations

    the phrase "Read more"

    oai_token-act-pair · gemini-2.0-flash

    Read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Read
    -0.78
     myſelf
    -0.73
     PublicKey
    -0.66
     Monfieur
    -0.65
    __*/
    -0.65
    Read
    -0.63
     reaſon
    -0.62
    ISupport
    -0.60
     itſelf
    -0.59
     iſt
    -0.59
    POSITIVE LOGITS
    StructEnd
    0.61
    ftagPool
    0.55
     مشين
    0.54
    akam
    0.53
     presentes
    0.52
     Winds
    0.50
     للمعارف
    0.50
    AndEndTag
    0.50
    تفصیلات
    0.49
    &
    0.49
    Activations Density 0.400%

    No Known Activations