© 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. 14688
    Prev
    Next
    INDEX
    Explanations

    code-related output, particularly formatted strings showing questions with categories, answers, bad answers, and error messages

    oai_token-act-pair · gemini-2.0-flash

    technical keywords or jargon

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

    : or =

    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
     estekak
    -0.73
    setCharacter
    -0.58
    :
    -0.57
     surla
    -0.57
    ":
    -0.54
    ='';
    -0.54
     JpaRepository
    -0.53
    :");
    -0.52
    ':
    -0.52
     ‘
    -0.50
    POSITIVE LOGITS
    TagMode
    0.68
    Rhestr
    0.65
    WriteBarrier
    0.57
    ̸
    0.51
    EMPL
    0.51
    WarningLevel
    0.50
     sanguí
    0.50
    홉
    0.50
    Persön
    0.49
    Magenta
    0.49
    Activations Density 6.125%

    No Known Activations