© 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. 9163
    Prev
    Next
    INDEX
    Explanations

    words related to personal pronouns and death

    oai_token-act-pair · gemini-2.0-flash

    unconventional or foreign words

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

    Technical descriptions/mixed languages

    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
     postales
    -0.54
    AutoField
    -0.49
    Tazama
    -0.47
    extField
    -0.44
    Anhalt
    -0.43
    Settings
    -0.43
    lamabad
    -0.42
     cartaz
    -0.41
    PROBLEM
    -0.41
    Сылтамалар
    -0.41
    POSITIVE LOGITS
    rungsseite
    0.83
    Portail
    0.80
    الحياه
    0.67
    bootstrapcdn
    0.66
     themſelves
    0.64
     Jefus
    0.63
     raiſ
    0.60
     ſever
    0.60
     ویکی‌پدی
    0.59
    verwijspagina
    0.59
    Activations Density 0.642%

    No Known Activations