© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6847
    Prev
    Next
    INDEX
    Explanations

    opinion and reporting language, particularly on negative or potentially controversial topics.

    oai_token-act-pair · gemini-2.0-flash

    describe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    andt
    -0.45
    L
    -0.40
    այ
    -0.38
    zahl
    -0.38
    idik
    -0.38
    >>
    -0.37
    >>>>
    -0.37
    ЕТ
    -0.36
    ReusableCell
    -0.36
    ету
    -0.36
    POSITIVE LOGITS
     described
    2.42
     describe
    2.31
     description
    2.22
     describes
    2.16
     Described
    2.08
    described
    2.08
     descriptions
    2.05
     DESCR
    2.00
     describing
    2.00
     descrito
    1.99
    Activations Density 3.062%

    No Known Activations