© 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. 8306
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'European' and acronyms for European organizations

    oai_token-act-pair · gemini-2.0-flash

    text related to European entities or organizations

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

    European

    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
    WithMany
    -0.52
    OGND
    -0.51
     carica
    -0.46
    mybatisplus
    -0.46
    mobileqq
    -0.45
     inz
    -0.44
    Geplaatst
    -0.42
    Trop
    -0.42
     MonoBehaviour
    -0.41
     lenker
    -0.41
    POSITIVE LOGITS
    PDOException
    0.61
    glLoad
    0.61
    glTexCoord
    0.58
     Union
    0.58
    fony
    0.57
    UNION
    0.54
    colhead
    0.54
    Externí
    0.54
     union
    0.54
    )++;
    0.53
    Activations Density 0.831%

    No Known Activations