© 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. 10691
    Prev
    Next
    INDEX
    Explanations

    words related to Facebook's account kit in Croatian as well as English words ending in "dists"

    oai_token-act-pair · gemini-2.0-flash

    dists

    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
     ')[
    -0.65
     ?',
    -0.64
     ")[
    -0.59
     ?",
    -0.59
    "',
    -0.56
     }}-
    -0.54
    ")==
    -0.52
    "]:
    -0.52
    """.
    -0.52
    ческих
    -0.50
    POSITIVE LOGITS
    tvguidetime
    0.85
     protoimpl
    0.85
    migrationBuilder
    0.84
     Normdatei
    0.77
     autorytatywna
    0.73
     referenties
    0.73
     Roskov
    0.72
     gynhyrchwyd
    0.69
    AccessorTable
    0.69
    CodedInputStream
    0.65
    Activations Density 0.243%

    No Known Activations