© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5914
    Prev
    Next
    INDEX
    Explanations

    sentences talking about the process of creating something

    oai_token-act-pair · gemini-2.0-flash

    behind

    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
     يتيمه
    -0.76
     كومونز
    -0.63
    SourceChecksum
    -0.62
     Administrativna
    -0.61
     }}$}
    -0.60
    kmäler
    -0.58
    niająca
    -0.58
     محفوظة
    -0.57
    uesday
    -0.57
     Paglinawan
    -0.55
    POSITIVE LOGITS
     behind
    0.84
     dietro
    0.82
    Behind
    0.81
    behind
    0.81
     detrás
    0.74
     Behind
    0.66
     BEHIND
    0.63
     derrière
    0.59
     bakom
    0.55
     trás
    0.49
    Activations Density 0.831%

    No Known Activations