© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11255
    Prev
    Next
    INDEX
    Explanations

    phrases about actions that a person does or can do.

    oai_token-act-pair · gemini-2.0-flash

    please

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ResumeLayout
    -0.65
    HasAnnotation
    -0.63
    kuuta
    -0.58
    DrawerToggle
    -0.56
     ComVisible
    -0.54
    endregion
    -0.52
    abetes
    -0.52
    ManyToMany
    -0.52
    multer
    -0.51
    wiście
    -0.51
    POSITIVE LOGITS
     please
    2.91
    please
    2.48
     Please
    2.27
    Please
    2.19
     PLEASE
    2.05
    PLEASE
    1.81
     plz
    1.80
     pls
    1.77
     bitte
    1.66
     Bitte
    1.44
    Activations Density 4.375%

    No Known Activations