© 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. 13098
    Prev
    Next
    INDEX
    Explanations

    subjective statements about an object of discussion

    oai_token-act-pair · gemini-2.0-flash

    various situations/events

    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
    ContentAsync
    -0.47
    Gön
    -0.47
    וויק
    -0.46
    ʁ
    -0.46
    labelledby
    -0.46
    windowFixed
    -0.45
     yet
    -0.45
    甸
    -0.44
     Ph
    -0.43
    mo
    -0.42
    POSITIVE LOGITS
    มาะ
    0.68
    waltung
    0.63
     itſelf
    0.62
    oredCriteria
    0.60
     for
    0.59
     незавершена
    0.59
     myſelf
    0.58
     defaultstate
    0.58
     đối
    0.58
    .」
    0.57
    Activations Density 12.159%

    No Known Activations