© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16066
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to computers and technology, particularly questions or instructions related to software or hardware

    oai_token-act-pair · gemini-2.0-flash

    installing software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AutoScaleMode
    -0.58
     machine
    -0.54
    تقاوى
    -0.50
    Демо
    -0.49
     Réponses
    -0.49
     machines
    -0.49
     ComVisible
    -0.48
     propOrder
    -0.48
    )$-
    -0.48
    JpaRepository
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    0.68
     OMITBAD
    0.66
     Noire
    0.59
    withIdentifier
    0.56
     ModelExpression
    0.56
    \{\\
    0.53
    principalColumn
    0.52
    TagMode
    0.50
    وق
    0.50
    adalupe
    0.47
    Activations Density 6.156%

    No Known Activations