© 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. 9781
    Prev
    Next
    INDEX
    Explanations

    phrases meant to orient or direct a reader to useful information.

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb "to be"

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

    introductions

    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
    StoryboardSegue
    -0.74
    UnusedPrivate
    -0.62
    sizeCache
    -0.59
     ✭✭
    -0.56
     EconPapers
    -0.55
    Portale
    -0.55
     betweenstory
    -0.54
    queryInterface
    -0.54
    +:+
    -0.54
    Gives
    -0.53
    POSITIVE LOGITS
     are
    1.84
     is
    1.47
     were
    1.27
    are
    1.06
     estão
    1.00
     ARE
    0.96
     Are
    0.96
     jsou
    0.93
     sont
    0.92
     están
    0.90
    Activations Density 4.929%

    No Known Activations