© 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. 13886
    Prev
    Next
    INDEX
    Explanations

    words describing car features and models, in the context of advertising or reviews.

    oai_token-act-pair · gemini-2.0-flash

    Peugeot cars

    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
    uxxxx
    -0.76
    الإنجليزية
    -0.71
    LabelTagHelper
    -0.70
    ]")]
    -0.69
    ScopeManager
    -0.68
     &___
    -0.68
     समीक्षक
    -0.65
    
    -0.65
    alige
    -0.64
     Roskov
    -0.64
    POSITIVE LOGITS
     Sport
    0.47
     GenerationType
    0.47
    ANIUM
    0.41
    pinephrine
    0.40
     Urban
    0.39
    ſt
    0.39
    ttemberg
    0.38
     urban
    0.38
     Dynamic
    0.37
     AT
    0.36
    Activations Density 1.310%

    No Known Activations