© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 15322
    Prev
    Next
    INDEX
    Explanations

    positive reviews, opinions, and experiences about products or services

    oai_token-act-pair · gemini-2.0-flash

    Expressing positive sentiment

    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
     auffi
    -0.91
     ainfi
    -0.85
     purpoſe
    -0.84
     Efq
    -0.84
     pleaſure
    -0.82
     houſe
    -0.80
     ſte
    -0.78
     auroit
    -0.78
     ſch
    -0.78
     feroit
    -0.78
    POSITIVE LOGITS
     on
    0.68
     with
    0.60
     which
    0.59
    "]),
    0.57
     the
    0.57
    CodeAttribute
    0.56
     –
    0.56
    ,
    0.53
     in
    0.52
    "]));
    0.52
    Activations Density 3.638%

    No Known Activations