© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9573
    Prev
    Next
    INDEX
    Explanations

    text related to submitting films to a festival.

    oai_token-act-pair · gemini-2.0-flash

    film submissions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     submitted
    -2.42
     submission
    -2.34
     submit
    -2.34
     submitting
    -2.27
     submits
    -2.20
     Submit
    -2.16
    submitted
    -2.14
    submit
    -2.13
     Submission
    -2.13
    Submit
    -2.09
    POSITIVE LOGITS
     Polic
    0.47
    protos
    0.46
    dek
    0.45
     res
    0.45
    Ђ
    0.43
     hóa
    0.43
    zös
    0.43
     decora
    0.42
    ianti
    0.42
     cataract
    0.41
    Activations Density 2.422%

    No Known Activations