© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13874
    Prev
    Next
    INDEX
    Explanations

    a mix of proper nouns, hyphenated phrases and possibly terms related to physical science

    oai_token-act-pair · gemini-2.0-flash

    Non-English texts

    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
    Local
    -0.24
    with
    -0.24
    ख्य
    -0.24
    קישורים
    -0.24
     and
    -0.23
    וויק
    -0.23
     glass
    -0.23
    local
    -0.23
     eing
    -0.23
    atoire
    -0.23
    POSITIVE LOGITS
     pleaſure
    0.91
     purpoſe
    0.91
     ſmall
    0.87
     Efq
    0.87
     Anſ
    0.87
     houſe
    0.86
     feroit
    0.85
     reaſon
    0.85
     Diſ
    0.84
     Houſe
    0.84
    Activations Density 13.690%

    No Known Activations