© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13692
    Prev
    Next
    INDEX
    Explanations

    comparative analysis and quantification.

    oai_token-act-pair · gemini-2.0-flash

    largest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    iglie
    -0.54
     navideñas
    -0.53
    ombie
    -0.51
    Kav
    -0.51
    #+#
    -0.49
    INCLUDES
    -0.48
    Roboto
    -0.48
    glEnd
    -0.48
     mummy
    -0.48
    getMenuInflater
    -0.48
    POSITIVE LOGITS
    GraphicsUnit
    0.63
    SerializedSize
    0.61
    StructEnd
    0.55
     capacity
    0.52
    SizeF
    0.52
    AutoScale
    0.52
     ModelExpression
    0.51
     consentimento
    0.50
     oprot
    0.49
    Izvori
    0.48
    Activations Density 9.715%

    No Known Activations