© 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. 7388
    Prev
    Next
    INDEX
    Explanations

    ordinary speech and words people say to each other in real life

    oai_token-act-pair · gemini-2.0-flash

    technical and specific terminology

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

    switching

    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
     hâte
    -0.64
     linkovi
    -0.62
    Personensuche
    -0.61
     mukana
    -0.61
     RIPRODUZIONE
    -0.60
     becauſe
    -0.59
     gouver
    -0.57
     communs
    -0.57
     himſelf
    -0.56
     myſelf
    -0.56
    POSITIVE LOGITS
    TabIndex
    0.64
    migrationBuilder
    0.61
     Biro
    0.58
    粟
    0.57
    Notae
    0.57
     Bundes
    0.57
     sachets
    0.54
    SWG
    0.54
     obstante
    0.53
     reckoned
    0.53
    Activations Density 3.260%

    No Known Activations