© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7863
    Prev
    Next
    INDEX
    Explanations

    mentions of gene modification in scientific writing, specifically relating to the terminus of a protein and the presence of tags or specific genes.

    oai_token-act-pair · gemini-2.0-flash

    front or rear

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    :+:
    -0.60
    #+#
    -0.48
     paging
    -0.46
     pageable
    -0.46
     nomme
    -0.44
    клопе
    -0.44
    kwds
    -0.43
    ässig
    -0.43
     Yosemite
    -0.42
    TextBoxColumn
    -0.42
    POSITIVE LOGITS
     front
    1.41
    front
    1.27
    Front
    1.24
     rear
    1.24
     Front
    1.23
     FRONT
    1.16
    FRONT
    1.09
     fronts
    1.05
    rear
    0.96
    Rear
    0.93
    Activations Density 1.629%

    No Known Activations