© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12166
    Prev
    Next
    INDEX
    Explanations

    scientific journal references

    oai_token-act-pair · gemini-2.0-flash

    journal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ried
    -0.50
    mopol
    -0.48
    dering
    -0.47
     sca
    -0.46
    agara
    -0.45
     estric
    -0.44
    idu
    -0.44
    NOWLEDG
    -0.43
    CreateMap
    -0.42
     nā
    -0.42
    POSITIVE LOGITS
     ""],
    0.98
    tagHelperRunner
    0.93
     للمعارف
    0.81
    UnitTesting
    0.81
    Билгалдахарш
    0.77
     Normdatei
    0.76
    estacks
    0.76
    iastes
    0.76
    __":
    0.76
    <bos>
    0.74
    Activations Density 1.548%

    No Known Activations