© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7610
    Prev
    Next
    INDEX
    Explanations

    medical and scientific language, particularly related to pharmaceuticals and body functions.

    oai_token-act-pair · gemini-2.0-flash

    Non-English / formatted text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     “
    -1.56
    ”
    -1.48
    “
    -1.41
     ‘
    -1.41
    —“
    -1.38
    …”
    -1.35
     “…
    -1.30
    –
    -1.28
     –
    -1.28
    ”—
    -1.26
    POSITIVE LOGITS
     feroit
    0.59
     fidé
    0.59
    égard
    0.54
     is
    0.53
     médec
    0.52
     chinese
    0.52
     are
    0.51
     pouvoit
    0.51
     dévelo
    0.49
     auroit
    0.49
    Activations Density 9.087%

    No Known Activations