© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11991
    Prev
    Next
    INDEX
    Explanations

    combinations of numbers and words like "both," "all," and "which."

    oai_token-act-pair · gemini-2.0-flash

    all, both, each

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    AccessorTable
    -0.96
     AssemblyTitle
    -0.93
    StructEnd
    -0.91
    HostException
    -0.85
    Geplaatst
    -0.85
    帖最后由
    -0.83
    AutoScaleMode
    -0.82
    bootstrapcdn
    -0.81
    adpleegd
    -0.79
     للاسماء
    -0.79
    POSITIVE LOGITS
     must
    0.45
     im
    0.44
     short
    0.43
     חיצוניים
    0.43
     did
    0.43
     nur
    0.41
     later
    0.39
     dallo
    0.39
     back
    0.38
     mu
    0.38
    Activations Density 0.342%

    No Known Activations