© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9476
    Prev
    Next
    INDEX
    Explanations

    descriptions of serious physical harm or death occurring to people, potentially victims of violence, and associated official investigations

    oai_token-act-pair · gemini-2.0-flash

    Transfers and actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     ujednoznacz
    -0.92
    GEBURTSDATUM
    -0.88
    ########.
    -0.79
     HasFactory
    -0.77
    ptonshire
    -0.70
     nakalista
    -0.69
    دانشنامهٔ
    -0.68
     дописавши
    -0.66
     itſelf
    -0.66
     оригіналу
    -0.65
    POSITIVE LOGITS
     صوتيه
    0.45
     вы
    0.42
     kdy
    0.42
    tidaknya
    0.40
    digan
    0.40
     laikā
    0.39
     jotka
    0.38
     anderem
    0.37
     saada
    0.36
     sent
    0.36
    Activations Density 2.626%

    No Known Activations