© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7124
    Prev
    Next
    INDEX
    Explanations

    the word "type" and shell script commands

    oai_token-act-pair · gemini-2.0-flash

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    type
    -2.16
     type
    -2.03
     TYPE
    -1.41
    TYPE
    -1.39
     types
    -1.34
     tipo
    -1.32
    类型
    -1.31
    types
    -1.30
     Type
    -1.25
    setType
    -1.20
    POSITIVE LOGITS
     >=",
    0.81
    SourceChecksum
    0.66
    setVerticalGroup
    0.66
    featureID
    0.64
    RegistryLite
    0.61
    ruptedException
    0.58
    WithIOException
    0.56
    octanol
    0.55
     ModelExpression
    0.54
     ContentValues
    0.53
    Activations Density 0.275%

    No Known Activations