© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10558
    Prev
    Next
    INDEX
    Explanations

    words related to population genetics

    oai_token-act-pair · gemini-2.0-flash

    differentiation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    AndEndTag
    -0.52
    Попис
    -0.51
     SPDX
    -0.51
    исленность
    -0.50
    truction
    -0.49
    ättern
    -0.49
    ibol
    -0.47
     الحره
    -0.47
    catel
    -0.47
    sistant
    -0.47
    POSITIVE LOGITS
     Patro
    0.62
     Conch
    0.61
     thistle
    0.60
     Purg
    0.59
     Ronan
    0.59
     Phry
    0.57
     skulls
    0.57
     Charlemagne
    0.56
     Etr
    0.56
     swallow
    0.56
    Activations Density 1.193%

    No Known Activations