© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9385
    Prev
    Next
    INDEX
    Explanations

    the word "is" and other forms of the verb "to be".

    oai_token-act-pair · gemini-2.0-flash

    Importance/necessity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Referencies
    -0.50
    aligned
    -0.48
    enda
    -0.47
     Rasen
    -0.44
    rited
    -0.44
    のか
    -0.43
    허
    -0.43
    ana
    -0.43
    acker
    -0.41
    akin
    -0.41
    POSITIVE LOGITS
    principalColumn
    0.83
     CreateTagHelper
    0.82
    DispatchToProps
    0.78
    ConstraintMaker
    0.76
     للاسماء
    0.74
     useStyles
    0.73
     Вікі
    0.71
    AutoScaleMode
    0.70
    NewUrlParser
    0.70
     kasarigan
    0.68
    Activations Density 0.837%

    No Known Activations