© 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. 3276
    Prev
    Next
    INDEX
    Explanations

    sentences that contain words indicating subjective evaluation and outcomes

    oai_token-act-pair · gemini-2.0-flash

    the word "when"

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

    when

    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
    HasAnnotation
    -0.59
    <?
    -0.55
    期刊论文
    -0.41
    Père
    -0.40
    Lähteet
    -0.39
    matta
    -0.38
    enskap
    -0.37
    codegen
    -0.37
    cshtml
    -0.37
    lanmış
    -0.37
    POSITIVE LOGITS
     when
    2.52
    when
    2.17
     quando
    2.11
     cuando
    2.03
     когда
    2.02
     When
    1.84
    When
    1.84
     WHEN
    1.80
     lorsque
    1.75
    cuando
    1.68
    Activations Density 6.741%

    No Known Activations