© 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. 8541
    Prev
    Next
    INDEX
    Explanations

    phrases that involve "checking" or "examining" or direction.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "see"

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

    to

    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
     utafitiHapana
    -0.73
    unknownFields
    -0.64
     Paglinawan
    -0.59
    AsUp
    -0.54
     internetowa
    -0.54
    μως
    -0.52
    Unnamed
    -0.52
     ujednoznacz
    -0.52
     يتيمه
    -0.51
    données
    -0.51
    POSITIVE LOGITS
     see
    1.98
     sees
    1.63
    see
    1.60
     See
    1.51
     seeing
    1.50
    See
    1.49
     seen
    1.43
     SEE
    1.30
     saw
    1.20
    SEE
    1.18
    Activations Density 2.781%

    No Known Activations