© 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. 2514
    Prev
    Next
    INDEX
    Explanations

    sentences that contain a mix of new and old information.

    oai_token-act-pair · gemini-2.0-flash

    auxiliary verbs

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

    General 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
     always
    -1.19
     usually
    -1.14
     actually
    -1.08
    تقاوى
    -1.03
     definitely
    -0.98
    always
    -0.98
     ALWAYS
    -0.97
     still
    -0.97
     already
    -0.94
    actually
    -0.92
    POSITIVE LOGITS
     is
    0.71
     will
    0.51
     was
    0.49
     would
    0.47
     liggen
    0.45
     are
    0.44
     particulières
    0.43
     salarios
    0.40
     maneira
    0.38
     gustaría
    0.38
    Activations Density 6.810%

    No Known Activations