© 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. 13771
    Prev
    Next
    INDEX
    Explanations

    hexadecimal code

    oai_token-act-pair · gemini-2.0-flash

    x

    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
     «
    -0.48
     du
    -0.47
    makeConstraints
    -0.44
     d
    -0.42
     �
    -0.42
     ${\
    -0.41
    pu
    -0.40
     sur
    -0.40
     “
    -0.40
     pu
    -0.40
    POSITIVE LOGITS
     pleaſure
    1.13
     purpoſe
    1.09
     itſelf
    1.05
     myſelf
    1.05
     Monfieur
    1.05
     Majefty
    1.04
    ſelf
    0.97
     houſe
    0.93
     reaſon
    0.93
     Theſe
    0.91
    Activations Density 0.565%

    No Known Activations