© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11420
    Prev
    Next
    INDEX
    Explanations

    difficult to ascertain, but it seems to relate to names or certain sentence structures.

    oai_token-act-pair · gemini-2.0-flash

    Arabic text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     teme
    -0.68
     ModelExpression
    -0.67
     ene
    -0.66
     Kere
    -0.65
    hede
    -0.65
    elle
    -0.62
    lege
    -0.62
    ene
    -0.62
    sede
    -0.61
     nere
    -0.60
    POSITIVE LOGITS
    ispiel
    0.47
     Griswold
    0.47
     OMITBAD
    0.46
    splitlines
    0.43
    íncia
    0.42
     ilmo
    0.40
    szönöm
    0.40
    kuuta
    0.39
     löyty
    0.39
    ÑOS
    0.39
    Activations Density 0.674%

    No Known Activations