© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14817
    Prev
    Next
    INDEX
    Explanations

    words describing professions in healthcare and personal growth.

    oai_token-act-pair · gemini-2.0-flash

    therapy or coaching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Compat
    -0.53
    }))
    -0.51
    sendStatus
    -0.50
    }));
    -0.49
     unto
    -0.49
    "])
    -0.48
     verre
    -0.47
    ưa
    -0.46
     reply
    -0.45
     faim
    -0.45
    POSITIVE LOGITS
     ویکی‌پدی
    0.86
    Jeografia
    0.68
    Хьажоргаш
    0.68
    richTextPanel
    0.66
     propOrder
    0.63
    ioutil
    0.62
     unknownFields
    0.61
     виправивши
    0.61
    #+#
    0.60
    OGND
    0.60
    Activations Density 2.807%

    No Known Activations