© 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. 1975
    Prev
    Next
    INDEX
    Explanations

    a mix of titles like "Dr.", and the word "as", as well as various punctuation

    oai_token-act-pair · gemini-2.0-flash

    Code and queries

    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
     Ass
    -1.50
     ASS
    -1.48
     AS
    -1.44
     ASC
    -1.41
     ass
    -1.40
    Ass
    -1.39
     ASP
    -1.38
     Asp
    -1.30
    ASS
    -1.23
    ass
    -1.20
    POSITIVE LOGITS
     ")");
    0.60
    »).
    0.56
     ""));
    0.54
    )».
    0.53
     mại
    0.52
    >())
    0.52
    »),
    0.50
     "").
    0.50
    iedler
    0.49
     ""),
    0.49
    Activations Density 1.554%

    No Known Activations