© 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. 14680
    Prev
    Next
    INDEX
    Explanations

    bracketed letters followed by numbers and punctuation, possibly in a configuration file

    oai_token-act-pair · gemini-2.0-flash

    code and math

    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
    daille
    -0.50
    timore
    -0.44
    CPtr
    -0.42
    ...@
    -0.42
    ندق
    -0.40
    the
    -0.40
    zes
    -0.39
     hiz
    -0.39
    utul
    -0.39
    بوابة
    -0.38
    POSITIVE LOGITS
    GraphicsUnit
    0.82
    endphp
    0.74
    Билгалдахарш
    0.74
     nakalista
    0.74
    astify
    0.73
    StoryboardSegue
    0.73
     مشين
    0.71
     CanadaChoose
    0.71
    ]")]
    0.71
     daihatsu
    0.70
    Activations Density 9.630%

    No Known Activations