© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10118
    Prev
    Next
    INDEX
    Explanations

    things like ratings from publications

    oai_token-act-pair · gemini-2.0-flash

    words related to star ratings

    np_token-act-pair-logits · gpt-4o-mini

    star

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ViewImports
    -0.61
    BeginContext
    -0.55
    WebControls
    -0.44
    ScopeManager
    -0.43
    ={},
    -0.42
    ResumeLayout
    -0.40
     typedef
    -0.39
    XtraBars
    -0.39
     bén
    -0.39
     Scotts
    -0.39
    POSITIVE LOGITS
     star
    2.58
     stars
    2.39
     Star
    2.14
    star
    2.06
     Stars
    2.03
    Star
    1.99
    stars
    1.98
     STAR
    1.96
    Stars
    1.88
     estrellas
    1.84
    Activations Density 2.135%

    No Known Activations