© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14402
    Prev
    Next
    INDEX
    Explanations

    something difficult to summarize, but it could be described as tracking violence, and recovery from violence, in a fantastical setting

    oai_token-act-pair · 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
    LookAnd
    -1.05
    MemoryWarning
    -0.94
     كومونز
    -0.94
    TemporalType
    -0.87
    UnusedPrivate
    -0.85
     betweenstory
    -0.84
    SequentialGroup
    -0.81
    GraphicsUnit
    -0.81
    featureID
    -0.79
    +#+#
    -0.77
    POSITIVE LOGITS
     sat
    0.52
     عمومی
    0.48
     master
    0.47
     ha
    0.46
     tamu
    0.46
     B
    0.46
     primary
    0.45
     bộ
    0.45
     H
    0.45
     „
    0.45
    Activations Density 6.776%

    No Known Activations