© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10442
    Prev
    Next
    INDEX
    Explanations

    C code documentation block headers

    oai_token-act-pair · gemini-2.0-flash

    code or documentation comments

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

    code/non-English 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_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
    mer
    -0.52
    └──
    -0.51
    gal
    -0.49
    ela
    -0.47
    mu
    -0.47
    mul
    -0.46
     -
    -0.46
    af
    -0.46
    ley
    -0.45
    種
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.66
     itſelf
    0.65
    +#+#
    0.65
    NUMX
    0.63
     disambiguazione
    0.62
     LUMP
    0.62
     himo
    0.61
     يتيمه
    0.61
    clusal
    0.60
    dafx
    0.60
    Activations Density 0.916%

    No Known Activations