© 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. 15970
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and forward slashes

    oai_token-act-pair · gemini-2.0-flash

    Number 3

    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
    <bos>
    -0.82
     mergeFrom
    -0.57
    //
    -0.46
    #
    -0.44
    Datuak
    -0.43
    ⓧ
    -0.43
    OGND
    -0.42
     commerciales
    -0.42
    Всем
    -0.40
     locul
    -0.40
    POSITIVE LOGITS
    ticons
    0.61
    eqn
    0.59
     Bute
    0.58
    AIRES
    0.55
     useContext
    0.54
    Hentet
    0.54
    DeleteBehavior
    0.54
    ^_^
    0.54
     AnyObject
    0.53
     Hond
    0.53
    Activations Density 2.432%

    No Known Activations