© 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. 12735
    Prev
    Next
    INDEX
    Explanations

    words about humanity and the earth

    oai_token-act-pair · gemini-2.0-flash

    mankind

    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
     
    -0.78
    #
    -0.56
    \
    -0.55
    &
    -0.53
     O
    -0.52
    .
    -0.51
    (
    -0.50
    _
    -0.50
    -
    -0.49
    $
    -0.48
    POSITIVE LOGITS
     Efq
    1.12
    ſelf
    1.02
     Houſe
    1.00
     ſtate
    0.99
     Theſe
    0.97
     Majefty
    0.96
     houſe
    0.96
     مشين
    0.96
     faſt
    0.96
     Jefus
    0.95
    Activations Density 0.989%

    No Known Activations