© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14786
    Prev
    Next
    INDEX
    Explanations

    words and phrases about diagnosis and treatment of medical problems

    oai_token-act-pair · gemini-2.0-flash

    treat

    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
     I
    -0.51
    ,
    -0.50
    aps
    -0.47
    -
    -0.46
     you
    -0.45
     i
    -0.44
     ed
    -0.44
    _
    -0.44
     use
    -0.43
    Friend
    -0.43
    POSITIVE LOGITS
    ArrowToggle
    0.93
     Efq
    0.88
     Theſe
    0.85
     fevere
    0.84
     ſche
    0.82
     lenker
    0.82
     pleaſure
    0.81
    extAlignment
    0.81
     Diſ
    0.80
     purpoſe
    0.80
    Activations Density 0.943%

    No Known Activations