© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9960
    Prev
    Next
    INDEX
    Explanations

    language associated with nonprofit organizations or advocacy groups

    oai_token-act-pair · gemini-2.0-flash

    programs

    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
    ValueStyle
    -1.02
    bootstrapcdn
    -0.73
    httphttps
    -0.68
    AnchorStyles
    -0.68
    Geplaatst
    -0.68
    ibatis
    -0.64
    Datuak
    -0.63
     estekak
    -0.62
    $_['
    -0.61
    ьаж
    -0.61
    POSITIVE LOGITS
     builds
    0.47
    }}/>
    0.45
    ]")]
    0.44
     pays
    0.43
    DOU
    0.43
    shadowOffset
    0.41
     />";
    0.40
    __))
    0.40
     connects
    0.39
    oughs
    0.39
    Activations Density 2.619%

    No Known Activations