© 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. 3470
    Prev
    Next
    INDEX
    Explanations

    sentences describing required actions, indicated by the word "must" or the infinitive form of a verb.

    oai_token-act-pair · gemini-2.0-flash

    procedural tasks or requirements

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

    must

    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
    itability
    -0.57
    )";
    -0.53
    sifs
    -0.51
    wenye
    -0.49
    iglio
    -0.48
    سطس
    -0.48
     चीज़ों
    -0.47
     "");
    -0.45
     ſtand
    -0.44
     dependen
    -0.44
    POSITIVE LOGITS
    下载附件
    0.67
    SequentialGroup
    0.65
    writeFieldEnd
    0.63
     indisponible
    0.63
    IVEREF
    0.62
     "..\..\..\
    0.57
     kotlin
    0.56
    "?>
    0.54
     Audiodateien
    0.53
     møte
    0.53
    Activations Density 1.845%

    No Known Activations