© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4729
    Prev
    Next
    INDEX
    Explanations

    casual conversational text with lots of personal pronouns and contractions

    oai_token-act-pair · gemini-2.0-flash

    non-english characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     '\\;'
    -0.73
     AttributeSet
    -0.70
    routeProvider
    -0.66
     tangerang
    -0.65
    nativeElement
    -0.64
    UnsafeEnabled
    -0.63
     ThemeData
    -0.63
     CGRectMake
    -0.63
     Autorisations
    -0.63
    RunWith
    -0.62
    POSITIVE LOGITS
     دیکھیے
    0.49
     ""
    0.49
     ''
    0.46
     ";"
    0.45
    /******/
    0.45
     "")
    0.42
     prav
    0.42
    ismu
    0.42
     ".";
    0.40
    addComponent
    0.40
    Activations Density 6.326%

    No Known Activations