© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11269
    Prev
    Next
    INDEX
    Explanations

    words of chemical formulae and thermochemistry

    oai_token-act-pair · gemini-2.0-flash

    thal

    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
     joaat
    -0.48
     feminino
    -0.48
    ſelf
    -0.47
     Diſ
    -0.45
     fubject
    -0.45
     barter
    -0.44
     للمعارف
    -0.44
     zda
    -0.44
     houſe
    -0.44
     miſ
    -0.43
    POSITIVE LOGITS
    #+#
    0.89
    Personensuche
    0.73
    featureID
    0.72
    تفصیلات
    0.69
    adaptiveStyles
    0.66
    gonic
    0.65
    kloped
    0.63
     ModelExpression
    0.60
    CloseOperation
    0.60
    HasForeignKey
    0.60
    Activations Density 1.252%

    No Known Activations