© 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. 15797
    Prev
    Next
    INDEX
    Explanations

    language about organizations and communities

    oai_token-act-pair · gemini-2.0-flash

    Sectors and groups

    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
    ⓘ
    -0.63
    DIPSETTING
    -0.57
    IsPostBack
    -0.55
    DaoImpl
    -0.52
    Beit
    -0.52
    esez
    -0.51
     Mele
    -0.50
    AutoScaleMode
    -0.50
     insuffisamment
    -0.50
    Referanser
    -0.49
    POSITIVE LOGITS
     виправивши
    0.70
    ]();
    0.54
    ensement
    0.54
    jmniej
    0.54
     tribes
    0.52
     sociologists
    0.52
     municipalities
    0.51
    RegistryLite
    0.51
     veterinarians
    0.51
     designers
    0.50
    Activations Density 5.289%

    No Known Activations