© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5296
    Prev
    Next
    INDEX
    Explanations

    words and phrases that emphasize that something is factual or real

    oai_token-act-pair · gemini-2.0-flash

    actually

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     actually
    -1.89
    actually
    -1.76
     Actually
    -1.59
    Actually
    -1.53
     ACTUALLY
    -1.51
     egentligen
    -1.27
     faktisk
    -1.25
     faktiskt
    -1.22
     realmente
    -1.20
     indeed
    -1.19
    POSITIVE LOGITS
    besar
    0.38
    umbo
    0.38
    기
    0.37
     mixte
    0.36
     mı
    0.36
    ளி
    0.36
     tiros
    0.36
    adpleegd
    0.36
     forno
    0.36
    findBy
    0.36
    Activations Density 0.590%

    No Known Activations