© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13152
    Prev
    Next
    INDEX
    Explanations

    a combination of technical language and possibly a conversational tone.

    oai_token-act-pair · gemini-2.0-flash

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Thereafter
    -0.87
     thereafter
    -0.86
     يتيمه
    -0.84
     successivamente
    -0.83
     потом
    -0.82
     Subsequent
    -0.81
     subsequent
    -0.81
     Afterwards
    -0.77
     Subsequently
    -0.76
     successivo
    -0.76
    POSITIVE LOGITS
     also
    0.52
     other
    0.52
     meanwhile
    0.47
     id
    0.47
     remain
    0.45
    さも
    0.44
    一方で
    0.43
    ūk
    0.42
    UnsafeEnabled
    0.42
     Tim
    0.42
    Activations Density 4.875%

    No Known Activations