© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13767
    Prev
    Next
    INDEX
    Explanations

    common short words, often prepositions and conjunctions, as well as the verb "to be".

    oai_token-act-pair · gemini-2.0-flash

    non-English or foreign language terms

    np_token-act-pair-logits · gpt-4o-mini

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    We
    -0.49
    masing
    -0.49
    they
    -0.47
    assertAll
    -0.46
    endwhile
    -0.45
    They
    -0.44
     endwhile
    -0.44
    All
    -0.43
    THEY
    -0.43
     Niro
    -0.43
    POSITIVE LOGITS
    Билгалдахарш
    0.89
     the
    0.88
     chi̍t
    0.83
    uxxxx
    0.81
    webElementXpaths
    0.74
     الحره
    0.74
    migrationBuilder
    0.72
    Autoritní
    0.70
    Erreferentziak
    0.66
     internetowa
    0.64
    Activations Density 14.886%

    No Known Activations